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

Update SpeedySpeech config

This commit is contained in:
Eren Gölge 2021-09-12 15:33:27 +00:00
parent bb69e714d0
commit 1ea011571a
2 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
README.md
View File

@ -73,6 +73,7 @@ Underlined "TTS*" and "Judy*" are 🐸TTS models
- Speedy-Speech: [paper](https://arxiv.org/abs/2008.03802) - Speedy-Speech: [paper](https://arxiv.org/abs/2008.03802)
- Align-TTS: [paper](https://arxiv.org/abs/2003.01950) - Align-TTS: [paper](https://arxiv.org/abs/2003.01950)
- FastPitch: [paper](https://arxiv.org/pdf/2006.06873.pdf) - FastPitch: [paper](https://arxiv.org/pdf/2006.06873.pdf)
- FastSpeech: [paper](https://arxiv.org/abs/1905.09263)
### End-to-End Models ### End-to-End Models
- VITS: [paper](https://arxiv.org/pdf/2106.06103) - VITS: [paper](https://arxiv.org/pdf/2106.06103)

4
TTS/tts/configs/speedy_speech_config.py
View File

@ -144,8 +144,8 @@ class SpeedySpeechConfig(BaseTTSConfig):
dur_loss_alpha: float = 1.0 dur_loss_alpha: float = 1.0
spec_loss_alpha: float = 1.0 spec_loss_alpha: float = 1.0
aligner_loss_alpha: float = 1.0 aligner_loss_alpha: float = 1.0
binary_align_loss_alpha: float = 1.0 binary_align_loss_alpha: float = 0.3
binary_align_loss_start_step: int = 20000 binary_align_loss_start_step: int = 50000
# overrides # overrides
min_seq_len: int = 13 min_seq_len: int = 13