Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Spaces:
Duplicated from
united-link/formosan-f5-tts
ithuan
/
formosan-f5-tts
like
0
Paused
App
Files
Files
Community
4
Fetching metadata from the HF Docker repository...
29c7e98
formosan-f5-tts
1.05 MB
2 contributors
History:
40 commits
txya900619
feat: replace torchaudio with torchcodec for audio decoding
29c7e98
4 months ago
configs
fix: models.yaml typo
6 months ago
ipa
fix: normalize some punctuation and special characters in text_to_ipa function
4 months ago
ref_wav
feat: add all-formosan-step-432640 model and use ref_wav lower than 12 sec
7 months ago
.gitattributes
Safe
1.56 kB
feat: update reference audio files and add new wav files
10 months ago
.gitignore
Safe
3.73 kB
feat: update g2p file path and add .gitignore
7 months ago
DEMO.md
Safe
686 Bytes
feat: add app.py
10 months ago
README.md
Safe
383 Bytes
docs: update readme models to current use
4 months ago
app.py
Safe
10 kB
feat: replace torchaudio with torchcodec for audio decoding
4 months ago
requirements.txt
Safe
68 Bytes
feat: replace torchaudio with torchcodec for audio decoding
4 months ago
