https://openvoice-tech.net/api.php?action=feedcontributions&feedformat=atom&user=Nmammedov 2026-05-08T14:55:21Z User contributions MediaWiki 1.43.1 https://openvoice-tech.net/index.php?title=General_TTS_tutorial&diff=2283 2022-03-07T14:06:56Z

<p>Nmammedov: /* Type of text to choose */</p> <hr /> <div>[[Category:TTS]]<br /> [[Category:HelloWorld]]<br /> This tutorial contains '''non-technical''' informations on TTS or Text-to-Speech. It's meant for all people who are new to the field of TTS and try to figure out which aspects to check or which possible ways to go.<br /> <br /> == Introduction ==<br /> TTS is an acronym that stands for '''T'''ext-'''T'''o-'''S'''peech technology which allows you to convert text to audio in the form of human speech. There are many different methods converting textual input to speech output. Some people use speech-synthesis to refer to TTS, they both mean the same thing. Currently, machile-learning method of text-to-speech conversion has become the dominant method of TTS. <br /> <br /> To use TTS you have two options based on the language you are targeting and based on whether the tool/service for your target language is already there or not. If you want to generate speech in a widely-used languages, there are TTS services developed for languages such as English, German, French, Russian etc. Major platforms such as Google, Windows support these languages by default. Then you can use these existing services to generate output. For example, you can try Google Translate if it speaks your language when you provide text input. This does not mean that all TTS technologies are available to you for free. It just means that it is likely that a free version also exists or can be built without too much effort using open-source technologies.<br /> <br /> If you are targeting a language which is not widely-used then it is likely that you will need to build a service that supports TTS function in your language. Usually, building a service means that you use open-source technologies and train the software to teach the computer to convert TTS in your language. There are well-developed open-source TTS platforms (examples?) out there which can be used if you are ready to invest your time and energy. This tutorial aims to provide general information for people who want to develop a TTS application for their language of choice. It can be useful for both widely-used and under-represented languages. <br /> <br /> To be more precise, this tutorial covers how to develop a TTS voice. Understanding TTS technology deeply requires significant amount of knowledge from computer science, linguistics, statistics disciplines. The technology in various forms and with diverse functionalities has been developed and is being used already. The purpose of this tutorial is to understand how to use the existing technology and apply them to a particular language. <br /> <br /> == Stages of training a TTS model ==<br /> There are several stages to build a TTS voice model. The order of these stages cannot be changed, unless one already has the output from a particular stage ready to proceed to the next stage.<br /> <br /> # Building a text dataset<br /> # Preparing a voice dataset using the text dataset<br /> # Training a TTS model using the voice dataset<br /> <br /> == Building a text dataset ==<br /> Training a TTS model requires text and voice dataset. To put it simply, TTS training aims to learn the relationship between text and sound and record that learned information in a file. Then when speech is synthesized the recorded information can be used to convert text to speech.<br /> <br /> === Type of text to choose ===<br /> When choosing text for the dataset it is important to think about the context in which the trained TTS model will be used. For example, if you use legal texts to train the model and then try to use the model to read everyday speech, then it may not meet your expectations. It is like training for competitions if one wants to compete in Olympic games then it is necessary to train at Olympic-standard sport facilities. The TTS learning program itself does not know anything about the language so it will be able to output only what was taught to it.<br /> <br /> Therefore, if one's goal is to synthesize speech from text in diverse domains it is necesary to include such texts in the dataset. For example, one can combine texts from different domains: 25% legal-normative-formal texts, 25% literature, fiction, poetry, 25% everyday conversations, 25% science-technology, art. The proportions and types can be chosen arbitrarily depending on the target use.<br /> <br /> ==== Language accents ====<br /> It is also important to keep in mind that written texts can have accents - different vocabularies, grammar differences that are still intelligible to people who speak other accents. For example, people from regions A and B of a country can use different words to refer to the same object and they may also have slightly different written forms of verbs. Therefore, if the target language of TTS model has such issues it is important to pay attention to addressing them - by using a standardized version of the language accepted by all speakers with different accents or by making sure that all accents are fairly represented in the text dataset.<br /> <br /> === Ensuring word-level diversity of text ===<br /> While choosing text from diverse domains is the first step of ensuring diversity, in fact, in some domains, especially in legal-formal texts, the words can be quite repetitive. The diversity of the text dataset must be at word level not at domain-category level. For example, if we want our TTS model to read all words with good quality then those words need to be fed to the system in the training phase.<br /> <br /> === Licensing issues ===<br /> It is important that text dataset has license that corresponds to its target use. Ideally, to ensure unlimited free use of the final output, text should be chosen from public domain. One widespread example of such a license is CC0 “No Rights Reserved”. To find &quot;no rights reserved&quot; texts one needs to look at the copyright legislation of the country in which the text dataset is being built. Usually, constitutions, laws, regulations, forms, directives are public domain texts. They are public domain by definition. In other domains usually the copyright expires after passage of a certain period of time, for instance, 50 years after the death of the author. By examining local legislation and researching it is usually possible to find sufficient amount of text with public domain rights. If the target use is proprietary (commercial), then one can agree with the authors of the texts included in the dataset to share benefits earned from the product. <br /> <br /> === Amount of text required ===<br /> The size of the text dataset depends on the size of the target voice dataset. Experts suggest that 25-40 hours of voice recordings are enough to build a good model. We can learn from the example of [https://keithito.com/LJ-Speech-Dataset/ LJ-Speech-Dataset] dataset to determine the amount of text we need to build our dataset. LJ-Speech dataset is 24 hours long, contains 13,100 sound clips with an average of 17 words in each clip. The total amount of words in the dataset is 225,715 and 13,821 of them are distinct words. To put it simply one needs about 13000 sentences of various lengths but with average number of 17 words in them. Emulating the example of LJ-Speech dataset can be useful for beginners because it has been tested by many TTS experts with good results.<br /> <br /> === Phoneme coverage ===<br /> Beside diversity check your text based on phoneme coverage for your language. A good coverage of all phonemes is recommended.<br /> <br /> === &lt;samp&gt;Punctuation mark&lt;/samp&gt; ===<br /> If you want your trained model to synthesize question or exclamation mark sentences which are pronounced different than normal sentences you should have question and exclamation marks in your text for recordings.<br /> <br /> == Preparing a voice dataset ==<br /> <br /> === Selecting a speaker ===<br /> Selecting a speaker to record the text dataset is the next step. Ideally, the ultimate TTS model being developed will speak exactly the way original speakers speaks. Make sure that the speaker's voice is &quot;pleasant&quot; to all listeners. Obviously it is impossible to get feedback from all future users, but there needs to be a reasonable effort to ensure that many listeners will be comfortable listening to the voice for long time and frequently. One way of achieving it is to record voices of speaker candidates and ask listeners opinion with an easy-to-understand scoring system. From technical perspective the voice does not matter for training. For example, if it is necessary for some reason to have a high-pitch voice, then it is perfectly okay.<br /> <br /> One important aspect of selecting a speaker is making sure that the speaker will be available for the entire duration of recording phase for the voice dataset. For instance, working with a person with good voice but a very busy schedule will not be good for the recording project. It is essential that the entire dataset is recorded by one person (voice).<br /> <br /> === Ethical issues ===<br /> There are ethical issues that one must be aware of when recording a voice. Voice is a distinct characteristic of a person's identity. Usually, it is possible to identify a known person from recorded sound. Ethical issues are related to potential use of TTS voices after they become ready. When they are made available for public use, users can use the voice to make it speak not only good texts but also bad texts including offensive, obscene, racist, and other illegal texts etc. Will the original speaker be comfortable with such use? Will there be a risk for the speaker? These questions must have clear answers. There are several ways to mitigate ethical issues. First thing to do is to inform the speaker fully of potential risks and secure his/her informed consent. Another measure is to select a relatively unknown person with a good voice and keep the person's identity anonymous. Third, make sure that legal disclaimers are in place for any malicious use of the voice. Fourth, work with and mobilize the community to monitor using of the model for only legal purposes.<br /> <br /> === Recording setup ===<br /> forthcoming<br /> <br /> <br /> ''The page is being developed. (sentence by sentence everyweek)''</div>

Nmammedov https://openvoice-tech.net/index.php?title=General_TTS_tutorial&diff=2270 2022-02-27T05:57:56Z

<p>Nmammedov: /* Text domain */</p> <hr /> <div>[[Category:TTS]]<br /> [[Category:HelloWorld]]<br /> This tutorial contains '''non-technical''' informations on TTS or Text-to-Speech. It's meant for all people who are new to the field of TTS and try to figure out which aspects to check or which possible ways to go.<br /> <br /> == Introduction ==<br /> TTS is an acronym that stands for '''T'''ext-'''T'''o-'''S'''peech technology which allows you to convert text to audio in the form of human speech. There are many different methods converting textual input to speech output. Some people use speech-synthesis to refer to TTS, they both mean the same thing. Currently, machile-learning method of text-to-speech conversion has become the dominant method of TTS. <br /> <br /> To use TTS you have two options based on the language you are targeting and based on whether the tool/service for your target language is already there or not. If you want to generate speech in a widely-used languages, there are TTS services developed for languages such as English, German, French, Russian etc. Major platforms such as Google, Windows support these languages by default. Then you can use these existing services to generate output. For example, you can try Google Translate if it speaks your language when you provide text input. This does not mean that all TTS technologies are available to you for free. It just means that it is likely that a free version also exists or can be built without too much effort using open-source technologies.<br /> <br /> If you are targeting a language which is not widely-used then it is likely that you will need to build a service that supports TTS function in your language. Usually, building a service means that you use open-source technologies and train the software to teach the computer to convert TTS in your language. There are well-developed open-source TTS platforms (examples?) out there which can be used if you are ready to invest your time and energy. This tutorial aims to provide general information for people who want to develop a TTS application for their language of choice. It can be useful for both widely-used and under-represented languages. <br /> <br /> To be more precise, this tutorial covers how to develop a TTS voice. Understanding TTS technology deeply requires significant amount of knowledge from computer science, linguistics, statistics disciplines. The technology in various forms and with diverse functionalities has been developed and is being used already. The purpose of this tutorial is to understand how to use the existing technology and apply them to a particular language. <br /> <br /> == Stages of training a TTS model ==<br /> There are several stages to build a TTS voice model. The order of these stages cannot be changed, unless one already has the output from a particular stage ready to proceed to the next stage.<br /> <br /> # Building a text dataset<br /> # Preparing a voice dataset using the text dataset<br /> # Training a TTS model using the voice dataset<br /> <br /> == Building a text dataset ==<br /> Training a TTS model requires text and voice dataset. To put it simply, TTS training aims to learn the relationship between text and sound and record that learned information in a file. Then when speech is synthesized the recorded information can be used to convert text to speech.<br /> <br /> === Type of text to choose ===<br /> When choosing text for the dataset it is important to think about the context in which the trained TTS model will be used. For example, if you use legal texts to train the model and then try to use the model to read everyday speech, then it may not meet your expectations. It is like training for competitions if one wants to compete in Olympic games then it is necessary to train at Olympic-standard sport facilities. The TTS learning program itself does not know anything about the language so it will be able to output only what was taught to it.<br /> <br /> Therefore, if one's goal is to synthesize speech from text in diverse domains it is necesary to include such texts in the dataset. For example, one can combine texts from different domains: 25% legal-normative-formal texts, 25% literature, fiction, poetry, 25% everyday conversations, 25% science-technology, art. The proportions and types can be chosen arbitrarily depending on the target use.<br /> <br /> === Ensuring word-level diversity of text ===<br /> While choosing text from diverse domains is the first step of ensuring diversity, in fact, in some domains, especially in legal-formal texts, the words can be quite repetitive. The diversity of the text dataset must be at word level not at domain-category level. For example, if we want our TTS model to read all words with good quality then those words need to be fed to the system in the training phase.<br /> <br /> === Licensing issues ===<br /> It is important that text dataset has license that corresponds to its target use. Ideally, to ensure unlimited free use of the final output, text should be chosen from public domain. One widespread example of such a license is CC0 “No Rights Reserved”. To find &quot;no rights reserved&quot; texts one needs to look at the copyright legislation of the country in which the text dataset is being built. Usually, constitutions, laws, regulations, forms, directives are public domain texts. They are public domain by definition. In other domains usually the copyright expires after passage of a certain period of time, for instance, 50 years after the death of the author. By examining local legislation and researching it is usually possible to find sufficient amount of text with public domain rights. If the target use is proprietary (commercial), then one can agree with the authors of the texts included in the dataset to share benefits earned from the product. <br /> <br /> === Amount of text required ===<br /> The size of the text dataset depends on the size of the target voice dataset. Experts suggest that 25-40 hours of voice recordings are enough to build a good model. We can learn from the example of [https://keithito.com/LJ-Speech-Dataset/ LJ-Speech-Dataset] dataset to determine the amount of text we need to build our dataset. LJ-Speech dataset is 24 hours long, contains 13,100 sound clips with an average of 17 words in each clip. The total amount of words in the dataset is 225,715 and 13,821 of them are distinct words. To put it simply one needs about 13000 sentences of various lengths but with average number of 17 words in them. Emulating the example of LJ-Speech dataset can be useful for beginners because it has been tested by many TTS experts with good results.<br /> <br /> <br /> <br /> ''The page is being developed. (sentence by sentence everyday)''</div>

Nmammedov https://openvoice-tech.net/index.php?title=General_TTS_tutorial&diff=2269 2022-02-23T14:42:22Z

<p>Nmammedov: </p> <hr /> <div>[[Category:TTS]]<br /> [[Category:HelloWorld]]<br /> This tutorial contains '''non-technical''' informations on TTS or Text-to-Speech. It's meant for all people who are new to the field of TTS and try to figure out which aspects to check or which possible ways to go.<br /> <br /> == Introduction ==<br /> TTS is an acronym that stands for '''T'''ext-'''T'''o-'''S'''peech technology which allows you to convert text to audio in the form of human speech. There are many different methods converting textual input to speech output. Some people use speech-synthesis to refer to TTS, they both mean the same thing. Currently, machile-learning method of text-to-speech conversion has become the dominant method of TTS. <br /> <br /> To use TTS you have two options based on the language you are targeting and based on whether the tool/service for your target language is already there or not. If you want to generate speech in a widely-used languages, there are TTS services developed for languages such as English, German, French, Russian etc. Major platforms such as Google, Windows support these languages by default. Then you can use these existing services to generate output. For example, you can try Google Translate if it speaks your language when you provide text input. This does not mean that all TTS technologies are available to you for free. It just means that it is likely that a free version also exists or can be built without too much effort using open-source technologies.<br /> <br /> If you are targeting a language which is not widely-used then it is likely that you will need to build a service that supports TTS function in your language. Usually, building a service means that you use open-source technologies and train the software to teach the computer to convert TTS in your language. There are well-developed open-source TTS platforms (examples?) out there which can be used if you are ready to invest your time and energy. This tutorial aims to provide general information for people who want to develop a TTS application for their language of choice. It can be useful for both widely-used and under-represented languages. <br /> <br /> To be more precise, this tutorial covers how to develop a TTS voice. Understanding TTS technology deeply requires significant amount of knowledge from computer science, linguistics, statistics disciplines. The technology in various forms and with diverse functionalities has been developed and is being used already. The purpose of this tutorial is to understand how to use the existing technology and apply them to a particular language. <br /> <br /> == Stages of training a TTS model ==<br /> There are several stages to build a TTS voice model. The order of these stages cannot be changed, unless one already has the output from a particular stage ready to proceed to the next stage.<br /> <br /> # Building a text dataset<br /> # Preparing a voice dataset using the text dataset<br /> # Training a TTS model using the voice dataset<br /> <br /> == Building a text dataset ==<br /> Training a TTS model requires text and voice dataset. To put it simply, TTS training aims to learn the relationship between text and sound and record that learned information in a file. Then when speech is synthesized the recorded information can be used to convert text to speech.<br /> <br /> === Text domain ===<br /> When choosing text for the dataset it is important to think about the context in which the trained TTS model will be used. For example, if you use legal texts to train the model and then try to use the model to read everyday speech, then it may not meet your expectations. It is like training for competitions if one wants to compete in Olympic games then it is necessary to train at Olympic-standard sport facilities. The TTS learning program itself does not know anything about the language so it will be able to output only what was taught to it.<br /> <br /> Therefore, if one's goal is to synthesize speech from text in diverse domains it is necesary to include such texts in the dataset. For example, one can combine texts from different domains: 25% legal-normative-formal texts, 25% literature, fiction, poetry, 25% everyday conversations, 25% science-technology, art. The proportions and types can be chosen arbitrarily depending on the target use.<br /> <br /> === Word-level diversity of text ===<br /> While choosing text from diverse domains is the first step of ensuring diversity, in fact, in some domains, especially in legal-formal texts, the words can be quite repetitive. The diversity of the text dataset must be at word level not at domain-category level. For example, if we want our TTS model to read all words with good quality then those words need to be fed to the system in the training phase.<br /> <br /> === Text license ===<br /> It is important that text dataset has license that corresponds to its target use. Ideally, to ensure unlimited free use of the final output, text should be chosen from public domain. One widespread example of such a license is CC0 “No Rights Reserved”. To find &quot;no rights reserved&quot; texts one needs to look at the copyright legislation of the country in which the text dataset is being built. Usually, constitutions, laws, regulations, forms, directives are public domain texts. They are public domain by definition. In other domains usually the copyright expires after passage of a certain period of time, for instance, 50 years after the death of the author. By examining local legislation and researching it is usually possible to find sufficient amount of text with public domain rights. If the target use is proprietary (commercial), then one can agree with the authors of the texts included in the dataset to share benefits earned from the product. <br /> <br /> === Text amount ===<br /> The size of the text dataset depends on the size of the target voice dataset. Experts suggest that 25-40 hours of voice recordings are enough to build a good model. We can learn from the example of [https://keithito.com/LJ-Speech-Dataset/ LJ-Speech-Dataset] dataset to determine the amount of text we need to build our dataset. LJ-Speech dataset is 24 hours long, contains 13,100 sound clips with an average of 17 words in each clip. The total amount of words in the dataset is 225,715 and 13,821 of them are distinct words. To put it simply one needs about 13000 sentences of various lengths but with average number of 17 words in them. Emulating the example of LJ-Speech dataset can be useful for beginners because it has been tested by many TTS experts with good results.<br /> <br /> <br /> <br /> ''The page is being developed. (sentence by sentence everyday)''</div>

Nmammedov https://openvoice-tech.net/index.php?title=General_TTS_tutorial&diff=2268 2022-02-23T14:28:05Z

<p>Nmammedov: </p> <hr /> <div>[[Category:TTS]]<br /> [[Category:HelloWorld]]<br /> This tutorial contains '''non-technical''' informations on TTS or Text-to-Speech. It's meant for all people who are new to the field of TTS and try to figure out which aspects to check or which possible ways to go.<br /> <br /> == Introduction ==<br /> TTS is an acronym that stands for '''T'''ext-'''T'''o-'''S'''peech technology which allows you to convert text to audio in the form of human speech. There are many different methods converting textual input to speech output. Some people use speech-synthesis to refer to TTS, they both mean the same thing. Currently, machile-learning method of text-to-speech conversion has become the dominant method of TTS. <br /> <br /> To use TTS you have two options based on the language you are targeting and based on whether the tool/service for your target language is already there or not. If you want to generate speech in a widely-used languages, there are TTS services developed for languages such as English, German, French, Russian etc. Major platforms such as Google, Windows support these languages by default. Then you can use these existing services to generate output. For example, you can try Google Translate if it speaks your language when you provide text input. This does not mean that all TTS technologies are available to you for free. It just means that it is likely that a free version also exists or can be built without too much effort using open-source technologies.<br /> <br /> If you are targeting a language which is not widely-used then it is likely that you will need to build a service that supports TTS function in your language. Usually, building a service means that you use open-source technologies and train the software to teach the computer to convert TTS in your language. There are well-developed open-source TTS platforms (examples?) out there which can be used if you are ready to invest your time and energy. This tutorial aims to provide general information for people who want to develop a TTS application for their language of choice. It can be useful for both widely-used and under-represented languages. <br /> <br /> To be more precise, this tutorial covers how to develop a TTS voice. Understanding TTS technology deeply requires significant amount of knowledge from computer science, linguistics, statistics disciplines. The technology in various forms and with diverse functionalities has been developed and is being used already. The purpose of this tutorial is to understand how to use the existing technology and apply them to a particular language. <br /> <br /> == Stages of training a TTS model ==<br /> There are several stages to build a TTS voice model. The order of these stages cannot be changed, unless one already has the output from a particular stage ready to proceed to the next stage.<br /> <br /> # Building a text dataset<br /> # Preparing a voice dataset using the text dataset<br /> # Training a TTS model using the voice dataset<br /> <br /> == Building a text dataset ==<br /> Training a TTS model requires text and voice dataset. To put it simply, TTS training aims to learn the relationship between text and sound and record that learned information in a file. Then when speech is synthesized the recorded information can be used to convert text to speech.<br /> <br /> === Text domain ===<br /> When choosing text for the dataset it is important to think about the context in which the trained TTS model will be used. For example, if you use legal texts to train the model and then try to use the model to read everyday speech, then it may not meet your expectations. It is like training for competitions if one wants to compete in Olympic games then it is necessary to train at Olympic-standard sport facilities. The TTS learning program itself does not know anything about the language so it will be able to output only what was taught to it.<br /> <br /> Therefore, if one's goal is to synthesize speech from text in diverse domains it is necesary to include such texts in the dataset. For example, one can combine texts from different domains: 25% legal-normative-formal texts, 25% literature, fiction, poetry, 25% everyday conversations, 25% science-technology, art. The proportions and types can be chosen arbitrarily depending on the target use.<br /> <br /> === Word-level diversity of text ===<br /> While choosing text from diverse domains is the first step of ensuring diversity, in fact, in some domains, especially in legal-formal texts, the words can be quite repetitive. The diversity of the text dataset must be at word level not at domain-category level. For example, if we want our TTS model to read all words with good quality then those words need to be fed to the system in the training phase.<br /> <br /> === Text license ===<br /> It is important that text dataset has license that correspond to its target use. Ideally, to ensure unlimited free use of the final output, text should be chosen from public domain. One widespread example of such a license is CC0 “No Rights Reserved”. To find &quot;no rights reserved&quot; texts one needs to look at the copyright legislation of the country in which the text dataset is being built. Usually, constitutions, laws, regulations, forms, directives are public domain texts. They are public domain by definition. In other domains usually the copyright expires after passage of a certain period of time, for instance, 50 years after the death of the author. By examining local legislation and researching it is usually possible to find sufficient amount of text with public domain rights. <br /> <br /> <br /> <br /> <br /> ''The page is being developed. (sentence by sentence everyday)''</div>

Nmammedov https://openvoice-tech.net/index.php?title=General_TTS_tutorial&diff=2267 2022-02-22T08:54:59Z

<p>Nmammedov: </p> <hr /> <div>[[Category:TTS]]<br /> [[Category:HelloWorld]]<br /> This tutorial contains '''non-technical''' informations on TTS or Text-to-Speech. It's meant for all people who are new to the field of TTS and try to figure out which aspects to check or which possible ways to go.<br /> <br /> == Introduction ==<br /> TTS is an acronym that stands for '''T'''ext-'''T'''o-'''S'''peech technology which allows you to convert text to audio in the form of human speech. There are many different methods converting textual input to speech output. Some people use speech-synthesis to refer to TTS, they both mean the same thing. Currently, machile-learning method of text-to-speech conversion has become the dominant method of TTS. <br /> <br /> To use TTS you have two options based on the language you are targeting and based on whether the tool/service for your target language is already there or not. If you want to generate speech in a widely-used languages, there are TTS services developed for languages such as English, German, French, Russian etc. Major platforms such as Google, Windows support these languages by default. Then you can use these existing services to generate output. For example, you can try Google Translate if it speaks your language when you provide text input. This does not mean that all TTS technologies are available to you for free. It just means that it is likely that a free version also exists or can be built without too much effort using open-source technologies.<br /> <br /> If you are targeting a language which is not widely-used then it is likely that you will need to build a service that supports TTS function in your language. Usually, building a service means that you use open-source technologies and train the software to teach the computer to convert TTS in your language. There are well-developed open-source TTS platforms (examples?) out there which can be used if you are ready to invest your time and energy. This tutorial aims to provide general information for people who want to develop a TTS application for their language of choice. It can be useful for both widely-used and under-represented languages. <br /> <br /> To be more precise, this tutorial covers how to develop a TTS voice. Understanding TTS technology deeply requires significant amount of knowledge from computer science, linguistics, statistics disciplines. The technology in various forms and with diverse functionalities has been developed and is being used already. The purpose of this tutorial is to understand how to use the existing technology and apply them to a particular language. <br /> <br /> == Stages of training a TTS model ==<br /> There are several stages to build a TTS voice model. The order of these stages cannot be changed, unless one already has the output from a particular stage ready to proceed to the next stage.<br /> <br /> # Building a text dataset<br /> # Preparing a voice dataset using the text dataset<br /> # Training a TTS model using the voice dataset<br /> <br /> == Building a text dataset ==<br /> Training a TTS model requires text and voice dataset. To put it simply, TTS training aims to learn the relationship between text and sound and record that learned information in a file. Then when speech is synthesized the recorded information can be used to convert text to speech.<br /> <br /> When choosing text for the dataset it is important to think about the context in which the trained TTS model will be used. For example, if you use legal texts to train the model and then use the model to read everyday speech, then it may not meet your expectations.<br /> <br /> <br /> ''The page is being developed.''</div>

Nmammedov https://openvoice-tech.net/index.php?title=General_TTS_tutorial&diff=2266 2022-02-21T10:03:57Z

<p>Nmammedov: </p> <hr /> <div>[[Category:TTS]]<br /> [[Category:HelloWorld]]<br /> This tutorial contains '''non-technical''' informations on TTS or Text-to-Speech. It's meant for all people who are new to the field of TTS and try to figure out which aspects to check or which possible ways to go.<br /> <br /> == Introduction ==<br /> TTS is an acronym that stands for '''T'''ext-'''T'''o-'''S'''peech technology which allows you to convert text to audio in the form of human speech. There are many different methods converting textual input to speech output. Some people use speech-synthesis to refer to TTS, they both mean the same thing. Currently, machile-learning method of text-to-speech conversion has become the dominant method of TTS. <br /> <br /> To use TTS you have two options based on the language you are targeting and based on whether the tool/service for your target language is already there or not. If you want to generate speech in a widely-used languages, there are TTS services developed for languages such as English, German, French, Russian etc. Major platforms such as Google, Windows support these languages by default. Then you can use these existing services to generate output. For example, you can try Google Translate if it speaks your language when you provide text input. This does not mean that all TTS technologies are available to you for free. It just means that it is likely that a free version also exists or can be built without too much effort using open-source technologies.<br /> <br /> If you are targeting a language which is not widely-used then it is likely that you will need to build a service that supports TTS function in your language. Usually, building a service means that you use open-source technologies and train the software to teach the computer to convert TTS in your language. There are well-developed open-source TTS platforms (examples?) out there which can be used if you are ready to invest your time and energy. This tutorial aims to provide general information for people who want to develop a TTS application for their language of choice. It can be useful for both widely-used and under-represented languages. <br /> <br /> To be more precise, this tutorial covers how to develop a TTS voice. Understanding TTS technology deeply requires significant amount of knowledge from computer science, linguistics, statistics disciplines. The technology in various forms and with diverse functionalities has been developed and is being used already. The purpose of this tutorial is to understand how to use the existing technology and apply them to a particular language. <br /> <br /> == Stages of training a TTS model ==<br /> There are several stages to build a TTS voice model. The order of these stages cannot be changed, unless one already has the output from a particular stage ready to proceed to the next stage.<br /> <br /> # Building a text dataset<br /> # Preparing a voice dataset using the text dataset<br /> # Training a TTS model using the voice dataset</div>

Nmammedov https://openvoice-tech.net/index.php?title=General_TTS_tutorial&diff=2265 2022-02-21T10:03:18Z

<p>Nmammedov: /* Introduction */</p> <hr /> <div>[[Category:TTS]]<br /> [[Category:HelloWorld]]<br /> This tutorial contains '''non-technical''' informations on TTS or Text-to-Speech. It's meant for all people who are new to the field of TTS and try to figure out which aspects to check or which possible ways to go.<br /> <br /> == Introduction ==<br /> TTS is an acronym that stands for '''T'''ext-'''T'''o-'''S'''peech technology which allows you to convert text to audio in the form of human speech. There are many different methods converting textual input to speech output. Some people use speech-synthesis to refer to TTS, they both mean the same thing. Currently, machile-learning method of text-to-speech conversion has become the dominant method of TTS. <br /> <br /> To use TTS you have two options based on the language you are targeting and based on whether the tool/service for your target language is already there or not. If you want to generate speech in a widely-used languages, there are TTS services developed for languages such as English, German, French, Russian etc. Major platforms such as Google, Windows support these languages by default. Then you can use these existing services to generate output. For example, you can try Google Translate if it speaks your language when you provide text input. This does not mean that all TTS technologies are available to you for free. It just means that it is likely that a free version also exists or can be built without too much effort using open-source technologies.<br /> <br /> If you are targeting a language which is not widely-used then it is likely that you will need to build a service that supports TTS function in your language. Usually, building a service means that you use open-source technologies and train the software to teach the computer to convert TTS in your language. There are well-developed open-source TTS platforms (examples?) out there which can be used if you are ready to invest your time and energy. This tutorial aims to provide general information for people who want to develop a TTS application for their language of choice. It can be useful for both widely-used and under-represented languages. <br /> <br /> To be more precise, this tutorial covers how to develop a TTS voice. Understanding TTS technology deeply requires significant amount of knowledge from computer science, linguistics, statistics disciplines. The technology in various forms and with diverse functionalities has been developed and is being used already. The purpose of this tutorial is to understand how to use the existing technology and apply them to a particular language. <br /> <br /> == Stages of training a TTS model ==<br /> There are several stages to build a TTS voice model. The order of these stages cannot be changed, unless one already has the output from a particular stage ready to proceed to the next stage.<br /> <br /> # Building a text dataset<br /> # Preparing a voice dataset using the text dataset<br /> # Training a TTS model used</div>

Nmammedov https://openvoice-tech.net/index.php?title=Talk:Main_Page&diff=2257 2022-02-18T08:22:42Z

<p>Nmammedov: /* Comprehensive TTS tutorial for newcomers */</p> <hr /> <div>== What infos on Mainpage? ==<br /> I'm not sure which content is helpful on Mainpage. Any ideas? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 08:46, 20 October 2021 (CEST)<br /> <br /> That's really important because is the landing page for a new user; some thoughts about it here below.<br /> <br /> In the home page I'd clarify a sort of &quot;manifesto&quot;, let me point out what I understand s far:<br /> <br /> 1- Openness: Open-source + open-data<br /> The wiki is dedicated to open* stuff. open-source/open-data. Two things a are obviously related. I absolutely agree and I'd stress this point, even if some concepts are independent from the openness, by example the concept of [[Conversation Design|conversational design]], or some basic glossary. <br /> <br /> 2- the wiki as web &quot;communication&quot; pattern<br /> <br /> - An how-to page section?<br /> Yo conceived this repo as a wiki, just &quot;a la wikipedia&quot; in all communication / content management. That' fully fair and I appreciate <br /> totally it but maybe it's not so clear to everyone involved. In my opinion the process that bringing a person to edit an existing page, or &quot;worst&quot;, to create a new page, is not trivial. My modest suggestion is to help reader (future author) with all kind of notes / remind in the pages, by example explaining the way to update a content using the discussion panel, etc. <br /> So maybe an &quot;HOW TO&quot; section could help<br /> <br /> - Video links<br /> Why to not link video of your youtube channel https://www.youtube.com/channel/UCjqqTVVBTsxpm0iOhQ1fp9g/videos? <br /> --[[User:Solyarisoftware|Solyarisoftware]] ([[User talk:Solyarisoftware|talk]]) 11:01, 12 December 2021 (CET)<br /> <br /> == General ideas on this wiki? ==<br /> <br /> What do you think? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 21:22, 1 November 2021 (CET)<br /> <br /> :This seems a really worthwhile initiative. Regarding the section for Voice related paper, maybe you already have thoughts on this, but I think it would be useful to recommend the kinds of detail desired (Title, Authors, DOI, source link(s), adding categories). Open links (eg Arxiv) would be preferred over those to non-free / subscription sites. Might also want to mention any preferences around pre-review/early access papers and handling updated versions and broken links. [[User:Nmstoker|Nmstoker]] ([[User talk:Nmstoker|talk]]) 14:06, 12 November 2021 (CET)<br /> ::Hello [[User:Nmstoker|Nmstoker]], i'm thinking of adding standard infobox templates for papers with that kind of informations you mentioned.--[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 20:23, 12 November 2021 (CET)<br /> <br /> :Another general thought: where do you stand on inclusion of opinion/original information in the wiki? Wikipedia is firmly about referencing information from sources, so they avoid hosting original information and only include things that are backed by references. I'm guessing that there may be grounds for more flexibility here, but deciding where to draw the line is worth considering. In a similar way, deciding where the line is between sharing knowledge vs excess promotion might need judgement. The key open source players do not strike me as being likely to over promote but there could be firms that aren't so reasonable, so having some kind of policy on this might help. [[User:Nmstoker|Nmstoker]] ([[User talk:Nmstoker|talk]]) 14:15, 12 November 2021 (CET)<br /> ::Copy'n Paste information from internetpages is not what i would prefer. Linking to sources seems is better. I'd hope that we can create a central knowledgebase for all open voice related projects and for that we have to add relevant information here. Over time we could vote some active users for being Admins here and help to control excessive promotion. --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 20:23, 12 November 2021 (CET)<br /> <br /> == Logo ideas ==<br /> <br /> As i'm a technology enthusiast, but truely not a design-guy the OpenVoice-Tech logo is &quot;functional&quot;. If you have ideas for a more attractive logo please help me :-). --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 19:12, 14 November 2021 (CET)<br /> <br /> == Added box with newest 5 articles on Mainpage ==<br /> <br /> Based on an idea from a nice guy at Mycroft community i've added a box containing the newest 5 articles on the Mainpage.--[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 07:17, 16 November 2021 (CET)<br /> <br /> == Added &quot;Contribution&quot; box on Mainpage ==<br /> <br /> If you would like to contribute to this Wiki i've added a box showing requested but not yet created pages on the Mainpage as a starting point. What do you think on this [[User:Eltocino|Eltocino]], [[User:Nmstoker|Nmstoker]], [[User:Florian|Florian]]? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 16:58, 19 November 2021 (CET)<br /> <br /> == Restructure categories ==<br /> <br /> Currently, it is hard for me to understand the basis chosen for the categories on the main page. I would have expected a high level separation of tools and concepts and underneath related subcategories, e.g., TTS and voice assistants under tools. [[User:Dirk|Dirk]] ([[User talk:Dirk|talk]]) 22:16, 10 January 2022 (CET)<br /> :Hi [[User:Dirk|Dirk]] thanks for your feedback. I've created the categories as i thought they would be helpful while setting up the wiki. I'm open to adjust/add/remove categories as content is increasing here. So you would think on &quot;OVT (Main category) --&gt; Tools --&gt; Voice Assistant&quot; for example? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 07:20, 11 January 2022 (CET)<br /> :: Let's discuss general thoughts on top-level categories [[Category_talk:Open_Voice_Tech|here]].--[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 17:25, 11 January 2022 (CET)<br /> <br /> == &quot;Quality datasets&quot; heading change ==<br /> <br /> The heading in categories is a bit misleading. Quality datasets takes us to Building quality dataset page. I suggest replacing &quot;Quality datasets&quot; with &quot;Building voice datasets&quot;. I think also quality should be part of any useful dataset so we can skip that word too.<br /> <br /> Building a dataset for TTS is a very important and not very simple topic, that can be added to categories. For many small languages this is the main barrier of entry.<br /> :You mean renaming page [[Quality_datasets]] to just &quot;Voice Datasets&quot;. Maybe we can skip the &quot;Building&quot;. What do you think? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 18:06, 11 January 2022 (CET)<br /> <br /> I think keeping &quot;Building&quot; is important if we include &quot;how to&quot; information in the page being referred to. If we say only &quot;Voice datasets&quot; then that page should include a list of ready-made available datasets. --[[User:Nmammedov|Nmammedov]] 18:06, 21 January 2022 (CET)<br /> <br /> == Comprehensive TTS tutorial for newcomers ==<br /> <br /> Please add the page which will include information for totally new beginners who don't know much about TTS but who are ready to commit time and energy to achieve the final result. The page will focus on<br /> * general introduction to TTS to prepare users mentally<br /> * building text dataset, text selection, editing, cleaning tips<br /> * building voice dataset, recording tips<br /> * training process, hardware software and other tips<br /> * testing/deploying the model<br /> * disseminating for public and using in other web/mobile applications<br /> <br /> The purpose of the tutorial is to make it as simple as possible for beginners and make sure that all stages of TTS from A-Z are covered. --[[User:Nmammedov|Nmammedov]] 18 February 2022 (CET)</div>

Nmammedov https://openvoice-tech.net/index.php?title=Talk:Main_Page&diff=2256 2022-02-18T08:12:56Z

<p>Nmammedov: /* Comprehensive TTS tutorial for newcomers */ new section</p> <hr /> <div>== What infos on Mainpage? ==<br /> I'm not sure which content is helpful on Mainpage. Any ideas? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 08:46, 20 October 2021 (CEST)<br /> <br /> That's really important because is the landing page for a new user; some thoughts about it here below.<br /> <br /> In the home page I'd clarify a sort of &quot;manifesto&quot;, let me point out what I understand s far:<br /> <br /> 1- Openness: Open-source + open-data<br /> The wiki is dedicated to open* stuff. open-source/open-data. Two things a are obviously related. I absolutely agree and I'd stress this point, even if some concepts are independent from the openness, by example the concept of [[Conversation Design|conversational design]], or some basic glossary. <br /> <br /> 2- the wiki as web &quot;communication&quot; pattern<br /> <br /> - An how-to page section?<br /> Yo conceived this repo as a wiki, just &quot;a la wikipedia&quot; in all communication / content management. That' fully fair and I appreciate <br /> totally it but maybe it's not so clear to everyone involved. In my opinion the process that bringing a person to edit an existing page, or &quot;worst&quot;, to create a new page, is not trivial. My modest suggestion is to help reader (future author) with all kind of notes / remind in the pages, by example explaining the way to update a content using the discussion panel, etc. <br /> So maybe an &quot;HOW TO&quot; section could help<br /> <br /> - Video links<br /> Why to not link video of your youtube channel https://www.youtube.com/channel/UCjqqTVVBTsxpm0iOhQ1fp9g/videos? <br /> --[[User:Solyarisoftware|Solyarisoftware]] ([[User talk:Solyarisoftware|talk]]) 11:01, 12 December 2021 (CET)<br /> <br /> == General ideas on this wiki? ==<br /> <br /> What do you think? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 21:22, 1 November 2021 (CET)<br /> <br /> :This seems a really worthwhile initiative. Regarding the section for Voice related paper, maybe you already have thoughts on this, but I think it would be useful to recommend the kinds of detail desired (Title, Authors, DOI, source link(s), adding categories). Open links (eg Arxiv) would be preferred over those to non-free / subscription sites. Might also want to mention any preferences around pre-review/early access papers and handling updated versions and broken links. [[User:Nmstoker|Nmstoker]] ([[User talk:Nmstoker|talk]]) 14:06, 12 November 2021 (CET)<br /> ::Hello [[User:Nmstoker|Nmstoker]], i'm thinking of adding standard infobox templates for papers with that kind of informations you mentioned.--[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 20:23, 12 November 2021 (CET)<br /> <br /> :Another general thought: where do you stand on inclusion of opinion/original information in the wiki? Wikipedia is firmly about referencing information from sources, so they avoid hosting original information and only include things that are backed by references. I'm guessing that there may be grounds for more flexibility here, but deciding where to draw the line is worth considering. In a similar way, deciding where the line is between sharing knowledge vs excess promotion might need judgement. The key open source players do not strike me as being likely to over promote but there could be firms that aren't so reasonable, so having some kind of policy on this might help. [[User:Nmstoker|Nmstoker]] ([[User talk:Nmstoker|talk]]) 14:15, 12 November 2021 (CET)<br /> ::Copy'n Paste information from internetpages is not what i would prefer. Linking to sources seems is better. I'd hope that we can create a central knowledgebase for all open voice related projects and for that we have to add relevant information here. Over time we could vote some active users for being Admins here and help to control excessive promotion. --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 20:23, 12 November 2021 (CET)<br /> <br /> == Logo ideas ==<br /> <br /> As i'm a technology enthusiast, but truely not a design-guy the OpenVoice-Tech logo is &quot;functional&quot;. If you have ideas for a more attractive logo please help me :-). --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 19:12, 14 November 2021 (CET)<br /> <br /> == Added box with newest 5 articles on Mainpage ==<br /> <br /> Based on an idea from a nice guy at Mycroft community i've added a box containing the newest 5 articles on the Mainpage.--[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 07:17, 16 November 2021 (CET)<br /> <br /> == Added &quot;Contribution&quot; box on Mainpage ==<br /> <br /> If you would like to contribute to this Wiki i've added a box showing requested but not yet created pages on the Mainpage as a starting point. What do you think on this [[User:Eltocino|Eltocino]], [[User:Nmstoker|Nmstoker]], [[User:Florian|Florian]]? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 16:58, 19 November 2021 (CET)<br /> <br /> == Restructure categories ==<br /> <br /> Currently, it is hard for me to understand the basis chosen for the categories on the main page. I would have expected a high level separation of tools and concepts and underneath related subcategories, e.g., TTS and voice assistants under tools. [[User:Dirk|Dirk]] ([[User talk:Dirk|talk]]) 22:16, 10 January 2022 (CET)<br /> :Hi [[User:Dirk|Dirk]] thanks for your feedback. I've created the categories as i thought they would be helpful while setting up the wiki. I'm open to adjust/add/remove categories as content is increasing here. So you would think on &quot;OVT (Main category) --&gt; Tools --&gt; Voice Assistant&quot; for example? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 07:20, 11 January 2022 (CET)<br /> :: Let's discuss general thoughts on top-level categories [[Category_talk:Open_Voice_Tech|here]].--[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 17:25, 11 January 2022 (CET)<br /> <br /> == &quot;Quality datasets&quot; heading change ==<br /> <br /> The heading in categories is a bit misleading. Quality datasets takes us to Building quality dataset page. I suggest replacing &quot;Quality datasets&quot; with &quot;Building voice datasets&quot;. I think also quality should be part of any useful dataset so we can skip that word too.<br /> <br /> Building a dataset for TTS is a very important and not very simple topic, that can be added to categories. For many small languages this is the main barrier of entry.<br /> :You mean renaming page [[Quality_datasets]] to just &quot;Voice Datasets&quot;. Maybe we can skip the &quot;Building&quot;. What do you think? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 18:06, 11 January 2022 (CET)<br /> <br /> I think keeping &quot;Building&quot; is important if we include &quot;how to&quot; information in the page being referred to. If we say only &quot;Voice datasets&quot; then that page should include a list of ready-made available datasets. --[[User:Nmammedov|Nmammedov]] 18:06, 21 January 2022 (CET)<br /> <br /> == Comprehensive TTS tutorial for newcomers ==<br /> <br /> Please add the page which will include information for totally new beginners who don't know much about TTS but who are ready to commit time and energy to achieve the final result. The page will focus on<br /> * general introduction to TTS to prepare users mentally<br /> * building text dataset, text selection, editing, cleaning tips<br /> * building voice dataset, recording tips<br /> * training process, hardware software and other tips<br /> * testing/deploying the model<br /> * disseminating for public and using in other web/mobile applications<br /> <br /> The purpose of the tutorial is to make it as simple as possible for beginners and make sure that all stages of TTS from A-Z are covered.</div>

Nmammedov https://openvoice-tech.net/index.php?title=Talk:Main_Page&diff=2237 2022-01-21T09:52:29Z

<p>Nmammedov: /* &quot;Quality datasets&quot; heading change */</p> <hr /> <div>== What infos on Mainpage? ==<br /> I'm not sure which content is helpful on Mainpage. Any ideas? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 08:46, 20 October 2021 (CEST)<br /> <br /> That's really important because is the landing page for a new user; some thoughts about it here below.<br /> <br /> In the home page I'd clarify a sort of &quot;manifesto&quot;, let me point out what I understand s far:<br /> <br /> 1- Openness: Open-source + open-data<br /> The wiki is dedicated to open* stuff. open-source/open-data. Two things a are obviously related. I absolutely agree and I'd stress this point, even if some concepts are independent from the openness, by example the concept of [[Conversation Design|conversational design]], or some basic glossary. <br /> <br /> 2- the wiki as web &quot;communication&quot; pattern<br /> <br /> - An how-to page section?<br /> Yo conceived this repo as a wiki, just &quot;a la wikipedia&quot; in all communication / content management. That' fully fair and I appreciate <br /> totally it but maybe it's not so clear to everyone involved. In my opinion the process that bringing a person to edit an existing page, or &quot;worst&quot;, to create a new page, is not trivial. My modest suggestion is to help reader (future author) with all kind of notes / remind in the pages, by example explaining the way to update a content using the discussion panel, etc. <br /> So maybe an &quot;HOW TO&quot; section could help<br /> <br /> - Video links<br /> Why to not link video of your youtube channel https://www.youtube.com/channel/UCjqqTVVBTsxpm0iOhQ1fp9g/videos? <br /> --[[User:Solyarisoftware|Solyarisoftware]] ([[User talk:Solyarisoftware|talk]]) 11:01, 12 December 2021 (CET)<br /> <br /> == General ideas on this wiki? ==<br /> <br /> What do you think? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 21:22, 1 November 2021 (CET)<br /> <br /> :This seems a really worthwhile initiative. Regarding the section for Voice related paper, maybe you already have thoughts on this, but I think it would be useful to recommend the kinds of detail desired (Title, Authors, DOI, source link(s), adding categories). Open links (eg Arxiv) would be preferred over those to non-free / subscription sites. Might also want to mention any preferences around pre-review/early access papers and handling updated versions and broken links. [[User:Nmstoker|Nmstoker]] ([[User talk:Nmstoker|talk]]) 14:06, 12 November 2021 (CET)<br /> ::Hello [[User:Nmstoker|Nmstoker]], i'm thinking of adding standard infobox templates for papers with that kind of informations you mentioned.--[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 20:23, 12 November 2021 (CET)<br /> <br /> :Another general thought: where do you stand on inclusion of opinion/original information in the wiki? Wikipedia is firmly about referencing information from sources, so they avoid hosting original information and only include things that are backed by references. I'm guessing that there may be grounds for more flexibility here, but deciding where to draw the line is worth considering. In a similar way, deciding where the line is between sharing knowledge vs excess promotion might need judgement. The key open source players do not strike me as being likely to over promote but there could be firms that aren't so reasonable, so having some kind of policy on this might help. [[User:Nmstoker|Nmstoker]] ([[User talk:Nmstoker|talk]]) 14:15, 12 November 2021 (CET)<br /> ::Copy'n Paste information from internetpages is not what i would prefer. Linking to sources seems is better. I'd hope that we can create a central knowledgebase for all open voice related projects and for that we have to add relevant information here. Over time we could vote some active users for being Admins here and help to control excessive promotion. --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 20:23, 12 November 2021 (CET)<br /> <br /> == Logo ideas ==<br /> <br /> As i'm a technology enthusiast, but truely not a design-guy the OpenVoice-Tech logo is &quot;functional&quot;. If you have ideas for a more attractive logo please help me :-). --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 19:12, 14 November 2021 (CET)<br /> <br /> == Added box with newest 5 articles on Mainpage ==<br /> <br /> Based on an idea from a nice guy at Mycroft community i've added a box containing the newest 5 articles on the Mainpage.--[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 07:17, 16 November 2021 (CET)<br /> <br /> == Added &quot;Contribution&quot; box on Mainpage ==<br /> <br /> If you would like to contribute to this Wiki i've added a box showing requested but not yet created pages on the Mainpage as a starting point. What do you think on this [[User:Eltocino|Eltocino]], [[User:Nmstoker|Nmstoker]], [[User:Florian|Florian]]? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 16:58, 19 November 2021 (CET)<br /> <br /> == Restructure categories ==<br /> <br /> Currently, it is hard for me to understand the basis chosen for the categories on the main page. I would have expected a high level separation of tools and concepts and underneath related subcategories, e.g., TTS and voice assistants under tools. [[User:Dirk|Dirk]] ([[User talk:Dirk|talk]]) 22:16, 10 January 2022 (CET)<br /> :Hi [[User:Dirk|Dirk]] thanks for your feedback. I've created the categories as i thought they would be helpful while setting up the wiki. I'm open to adjust/add/remove categories as content is increasing here. So you would think on &quot;OVT (Main category) --&gt; Tools --&gt; Voice Assistant&quot; for example? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 07:20, 11 January 2022 (CET)<br /> :: Let's discuss general thoughts on top-level categories [[Category_talk:Open_Voice_Tech|here]].--[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 17:25, 11 January 2022 (CET)<br /> <br /> == &quot;Quality datasets&quot; heading change ==<br /> <br /> The heading in categories is a bit misleading. Quality datasets takes us to Building quality dataset page. I suggest replacing &quot;Quality datasets&quot; with &quot;Building voice datasets&quot;. I think also quality should be part of any useful dataset so we can skip that word too.<br /> <br /> Building a dataset for TTS is a very important and not very simple topic, that can be added to categories. For many small languages this is the main barrier of entry.<br /> :You mean renaming page [[Quality_datasets]] to just &quot;Voice Datasets&quot;. Maybe we can skip the &quot;Building&quot;. What do you think? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 18:06, 11 January 2022 (CET)<br /> <br /> I think keeping &quot;Building&quot; is important if we include &quot;how to&quot; information in the page being referred to. If we say only &quot;Voice datasets&quot; then that page should include a list of ready-made available datasets. --[[User:Nmammedov|Nmammedov]] 18:06, 21 January 2022 (CET)</div>

Nmammedov https://openvoice-tech.net/index.php?title=Talk:Main_Page&diff=2220 2022-01-11T12:46:11Z

<p>Nmammedov: /* &quot;Quality datasets&quot; heading change */</p> <hr /> <div>== What infos on Mainpage? ==<br /> I'm not sure which content is helpful on Mainpage. Any ideas? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 08:46, 20 October 2021 (CEST)<br /> <br /> That's really important because is the landing page for a new user; some thoughts about it here below.<br /> <br /> In the home page I'd clarify a sort of &quot;manifesto&quot;, let me point out what I understand s far:<br /> <br /> 1- Openness: Open-source + open-data<br /> The wiki is dedicated to open* stuff. open-source/open-data. Two things a are obviously related. I absolutely agree and I'd stress this point, even if some concepts are independent from the openness, by example the concept of [[Conversation Design|conversational design]], or some basic glossary. <br /> <br /> 2- the wiki as web &quot;communication&quot; pattern<br /> <br /> - An how-to page section?<br /> Yo conceived this repo as a wiki, just &quot;a la wikipedia&quot; in all communication / content management. That' fully fair and I appreciate <br /> totally it but maybe it's not so clear to everyone involved. In my opinion the process that bringing a person to edit an existing page, or &quot;worst&quot;, to create a new page, is not trivial. My modest suggestion is to help reader (future author) with all kind of notes / remind in the pages, by example explaining the way to update a content using the discussion panel, etc. <br /> So maybe an &quot;HOW TO&quot; section could help<br /> <br /> - Video links<br /> Why to not link video of your youtube channel https://www.youtube.com/channel/UCjqqTVVBTsxpm0iOhQ1fp9g/videos? <br /> --[[User:Solyarisoftware|Solyarisoftware]] ([[User talk:Solyarisoftware|talk]]) 11:01, 12 December 2021 (CET)<br /> <br /> == General ideas on this wiki? ==<br /> <br /> What do you think? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 21:22, 1 November 2021 (CET)<br /> <br /> :This seems a really worthwhile initiative. Regarding the section for Voice related paper, maybe you already have thoughts on this, but I think it would be useful to recommend the kinds of detail desired (Title, Authors, DOI, source link(s), adding categories). Open links (eg Arxiv) would be preferred over those to non-free / subscription sites. Might also want to mention any preferences around pre-review/early access papers and handling updated versions and broken links. [[User:Nmstoker|Nmstoker]] ([[User talk:Nmstoker|talk]]) 14:06, 12 November 2021 (CET)<br /> ::Hello [[User:Nmstoker|Nmstoker]], i'm thinking of adding standard infobox templates for papers with that kind of informations you mentioned.--[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 20:23, 12 November 2021 (CET)<br /> <br /> :Another general thought: where do you stand on inclusion of opinion/original information in the wiki? Wikipedia is firmly about referencing information from sources, so they avoid hosting original information and only include things that are backed by references. I'm guessing that there may be grounds for more flexibility here, but deciding where to draw the line is worth considering. In a similar way, deciding where the line is between sharing knowledge vs excess promotion might need judgement. The key open source players do not strike me as being likely to over promote but there could be firms that aren't so reasonable, so having some kind of policy on this might help. [[User:Nmstoker|Nmstoker]] ([[User talk:Nmstoker|talk]]) 14:15, 12 November 2021 (CET)<br /> ::Copy'n Paste information from internetpages is not what i would prefer. Linking to sources seems is better. I'd hope that we can create a central knowledgebase for all open voice related projects and for that we have to add relevant information here. Over time we could vote some active users for being Admins here and help to control excessive promotion. --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 20:23, 12 November 2021 (CET)<br /> <br /> == Logo ideas ==<br /> <br /> As i'm a technology enthusiast, but truely not a design-guy the OpenVoice-Tech logo is &quot;functional&quot;. If you have ideas for a more attractive logo please help me :-). --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 19:12, 14 November 2021 (CET)<br /> <br /> == Added box with newest 5 articles on Mainpage ==<br /> <br /> Based on an idea from a nice guy at Mycroft community i've added a box containing the newest 5 articles on the Mainpage.--[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 07:17, 16 November 2021 (CET)<br /> <br /> == Added &quot;Contribution&quot; box on Mainpage ==<br /> <br /> If you would like to contribute to this Wiki i've added a box showing requested but not yet created pages on the Mainpage as a starting point. What do you think on this [[User:Eltocino|Eltocino]], [[User:Nmstoker|Nmstoker]], [[User:Florian|Florian]]? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 16:58, 19 November 2021 (CET)<br /> <br /> == Restructure categories ==<br /> <br /> Currently, it is hard for me to understand the basis chosen for the categories on the main page. I would have expected a high level separation of tools and concepts and underneath related subcategories, e.g., TTS and voice assistants under tools. [[User:Dirk|Dirk]] ([[User talk:Dirk|talk]]) 22:16, 10 January 2022 (CET)<br /> :Hi [[User:Dirk|Dirk]] thanks for your feedback. I've created the categories as i thought they would be helpful while setting up the wiki. I'm open to adjust/add/remove categories as content is increasing here. So you would think on &quot;OVT (Main category) --&gt; Tools --&gt; Voice Assistant&quot; for example? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 07:20, 11 January 2022 (CET)<br /> <br /> == &quot;Quality datasets&quot; heading change ==<br /> <br /> The heading in categories is a bit misleading. Quality datasets takes us to Building quality dataset page. I suggest replacing &quot;Quality datasets&quot; with &quot;Building voice datasets&quot;. I think also quality should be part of any useful dataset so we can skip that word too.<br /> <br /> Building a dataset for TTS is a very important and not very simple topic, that can be added to categories. For many small languages this is the main barrier of entry.</div>

Nmammedov https://openvoice-tech.net/index.php?title=Talk:Main_Page&diff=2219 2022-01-11T12:25:00Z

<p>Nmammedov: /* &quot;Quality datasets&quot; heading change */ new section</p> <hr /> <div>== What infos on Mainpage? ==<br /> I'm not sure which content is helpful on Mainpage. Any ideas? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 08:46, 20 October 2021 (CEST)<br /> <br /> That's really important because is the landing page for a new user; some thoughts about it here below.<br /> <br /> In the home page I'd clarify a sort of &quot;manifesto&quot;, let me point out what I understand s far:<br /> <br /> 1- Openness: Open-source + open-data<br /> The wiki is dedicated to open* stuff. open-source/open-data. Two things a are obviously related. I absolutely agree and I'd stress this point, even if some concepts are independent from the openness, by example the concept of [[Conversation Design|conversational design]], or some basic glossary. <br /> <br /> 2- the wiki as web &quot;communication&quot; pattern<br /> <br /> - An how-to page section?<br /> Yo conceived this repo as a wiki, just &quot;a la wikipedia&quot; in all communication / content management. That' fully fair and I appreciate <br /> totally it but maybe it's not so clear to everyone involved. In my opinion the process that bringing a person to edit an existing page, or &quot;worst&quot;, to create a new page, is not trivial. My modest suggestion is to help reader (future author) with all kind of notes / remind in the pages, by example explaining the way to update a content using the discussion panel, etc. <br /> So maybe an &quot;HOW TO&quot; section could help<br /> <br /> - Video links<br /> Why to not link video of your youtube channel https://www.youtube.com/channel/UCjqqTVVBTsxpm0iOhQ1fp9g/videos? <br /> --[[User:Solyarisoftware|Solyarisoftware]] ([[User talk:Solyarisoftware|talk]]) 11:01, 12 December 2021 (CET)<br /> <br /> == General ideas on this wiki? ==<br /> <br /> What do you think? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 21:22, 1 November 2021 (CET)<br /> <br /> :This seems a really worthwhile initiative. Regarding the section for Voice related paper, maybe you already have thoughts on this, but I think it would be useful to recommend the kinds of detail desired (Title, Authors, DOI, source link(s), adding categories). Open links (eg Arxiv) would be preferred over those to non-free / subscription sites. Might also want to mention any preferences around pre-review/early access papers and handling updated versions and broken links. [[User:Nmstoker|Nmstoker]] ([[User talk:Nmstoker|talk]]) 14:06, 12 November 2021 (CET)<br /> ::Hello [[User:Nmstoker|Nmstoker]], i'm thinking of adding standard infobox templates for papers with that kind of informations you mentioned.--[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 20:23, 12 November 2021 (CET)<br /> <br /> :Another general thought: where do you stand on inclusion of opinion/original information in the wiki? Wikipedia is firmly about referencing information from sources, so they avoid hosting original information and only include things that are backed by references. I'm guessing that there may be grounds for more flexibility here, but deciding where to draw the line is worth considering. In a similar way, deciding where the line is between sharing knowledge vs excess promotion might need judgement. The key open source players do not strike me as being likely to over promote but there could be firms that aren't so reasonable, so having some kind of policy on this might help. [[User:Nmstoker|Nmstoker]] ([[User talk:Nmstoker|talk]]) 14:15, 12 November 2021 (CET)<br /> ::Copy'n Paste information from internetpages is not what i would prefer. Linking to sources seems is better. I'd hope that we can create a central knowledgebase for all open voice related projects and for that we have to add relevant information here. Over time we could vote some active users for being Admins here and help to control excessive promotion. --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 20:23, 12 November 2021 (CET)<br /> <br /> == Logo ideas ==<br /> <br /> As i'm a technology enthusiast, but truely not a design-guy the OpenVoice-Tech logo is &quot;functional&quot;. If you have ideas for a more attractive logo please help me :-). --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 19:12, 14 November 2021 (CET)<br /> <br /> == Added box with newest 5 articles on Mainpage ==<br /> <br /> Based on an idea from a nice guy at Mycroft community i've added a box containing the newest 5 articles on the Mainpage.--[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 07:17, 16 November 2021 (CET)<br /> <br /> == Added &quot;Contribution&quot; box on Mainpage ==<br /> <br /> If you would like to contribute to this Wiki i've added a box showing requested but not yet created pages on the Mainpage as a starting point. What do you think on this [[User:Eltocino|Eltocino]], [[User:Nmstoker|Nmstoker]], [[User:Florian|Florian]]? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 16:58, 19 November 2021 (CET)<br /> <br /> == Restructure categories ==<br /> <br /> Currently, it is hard for me to understand the basis chosen for the categories on the main page. I would have expected a high level separation of tools and concepts and underneath related subcategories, e.g., TTS and voice assistants under tools. [[User:Dirk|Dirk]] ([[User talk:Dirk|talk]]) 22:16, 10 January 2022 (CET)<br /> :Hi [[User:Dirk|Dirk]] thanks for your feedback. I've created the categories as i thought they would be helpful while setting up the wiki. I'm open to adjust/add/remove categories as content is increasing here. So you would think on &quot;OVT (Main category) --&gt; Tools --&gt; Voice Assistant&quot; for example? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 07:20, 11 January 2022 (CET)<br /> <br /> == &quot;Quality datasets&quot; heading change ==<br /> <br /> The heading in categories is a bit misleading. Quality datasets takes us to Building quality dataset page. I suggest replacing &quot;Quality datasets&quot; with &quot;Building voice datasets&quot;. I think also quality should be part of any useful dataset so we can skip that word too.</div>

Nmammedov