Medix-AI/coqui-tts
Medix-AI
/
coqui-tts
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Adjust default to be able to process longer sentences (#1835) 

Running `tts --text "$text" --out_path …` with a somewhat longer
sentences in the text will lead to warnings like “Decoder stopped with
max_decoder_steps 500” and the sentences just being cut off in the
resulting WAV file.

This happens quite frequently when feeding longer texts (e.g. a blog
post) to `tts`. It's particular frustrating since the error is not
always obvious in the output. You have to notice that there are missing
parts. This is something other users seem to have run into as well [1].

This patch simply increases the maximum number of steps allowed for the
tacotron decoder to fix this issue, resulting in a smoother default
behavior.

[1] https://github.com/mozilla/TTS/issues/734
This commit is contained in:
Lars Kiesow 2022-08-07 13:51:29 +02:00 committed by GitHub
parent 903a77c197
commit 8c645080ac
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
TTS/tts/configs/tacotron_config.py
View File

@ -162,7 +162,7 @@ class TacotronConfig(BaseTTSConfig):
stopnet: bool = True stopnet: bool = True
separate_stopnet: bool = True separate_stopnet: bool = True
stopnet_pos_weight: float = 0.2 stopnet_pos_weight: float = 0.2
max_decoder_steps: int = 500 max_decoder_steps: int = 10000
encoder_in_features: int = 256 encoder_in_features: int = 256
decoder_in_features: int = 256 decoder_in_features: int = 256
decoder_output_dim: int = 80 decoder_output_dim: int = 80