Speaking issues Coqui TTS Tacotron2 DDC model: Difference between revisions
Jump to navigation
Jump to search
(Restructure and add section for mispronounced words) |
m (Rollback changes) Tags: Manual revert Visual edit |
||
| (2 intermediate revisions by the same user not shown) | |||
| Line 2: | Line 2: | ||
[[Category:TTS models]] | [[Category:TTS models]] | ||
[[Category:Pronunciation issues]] | [[Category:Pronunciation issues]] | ||
== 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. | |||
*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 | ||
==Input string formatting== | ==Input string formatting== | ||
Latest revision as of 23:44, 12 November 2021
General[edit | edit source]
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.
- TTS model: tts_models/en/ljspeech/tacotron2-DDC
- Vocoder model: vocoder_models/en/ljspeech/hifigan_v2
Input string formatting[edit | edit source]
Phrases ending in "ah"[edit | edit source]
"ah" at end of sentence generally produces strange results. Short names produce a 12 second clip.
Examples:
- Nelson Mandela
- pergola
Mitigation[edit | edit source]
If at the end of the input, adding punctuation to the end synthesizes correctly:
Example "Nelson Mandela" > "Nelson Mandela."
Acronyms[edit | edit source]
To speak acronyms as letters it needs to be formatted as:
"A. B. C. news"
Not:
"ABC news" "A.B.C. news"
Mispronounced Words[edit | edit source]
- video