Speaking issues Coqui TTS Tacotron2 DDC model: Difference between revisions
Created page with "Category:Coqui Category:TTS models Category:Pronunciation issues *TTS model: tts_models/en/ljspeech/tacotron2-DDC *Vocoder model: vocoder_models/en/ljspeech/hifig..." |
|||
| Line 5: | Line 5: | ||
*TTS model: tts_models/en/ljspeech/tacotron2-DDC | *TTS model: tts_models/en/ljspeech/tacotron2-DDC | ||
*Vocoder model: vocoder_models/en/ljspeech/hifigan_v2 | *Vocoder model: vocoder_models/en/ljspeech/hifigan_v2 | ||
== General == | |||
Most models are trained with a dot, exclamation or question mark at the end. So always end a sentence to avoid model synthesizing weird output. | |||
==nelson mandela== | ==nelson mandela== | ||
Revision as of 10:59, 20 October 2021
- TTS model: tts_models/en/ljspeech/tacotron2-DDC
- Vocoder model: vocoder_models/en/ljspeech/hifigan_v2
General
Most models are trained with a dot, exclamation or question mark at the end. So always end a sentence to avoid model synthesizing weird output.
nelson mandela
"ah" at end of sentence generally produces strange results. Just the name produces a 12 second clip.
pergola
"ah" at end of sentence generally produces strange results. Just the name produces a 12 second clip.
ABC news
To speak acronyms as letters it needs to be formatted as "A. B. C. news"