yl4579/AuxiliaryASR
Joint CTC-S2S Phoneme-level ASR for Voice Conversion and TTS (Text-Mel Alignment)
Combines CTC and sequence-to-sequence losses for robust phoneme recognition across speaker variation, enabling downstream voice conversion and TTS applications. Built on PyTorch with mel-spectrogram feature extraction, supporting multi-speaker training via speaker embeddings. Integrates with StarGANv2-VC and StyleTTS pipelines; extensible to non-English languages by swapping the g2p_en phonemizer and vocabulary files.
125 stars. No commits in the last 6 months.
Stars
125
Forks
48
Language
Python
License
MIT
Category
Last pushed
Jun 16, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/yl4579/AuxiliaryASR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
TensorSpeech/TensorFlowASR
:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2....
xinjli/allosaurus
Allosaurus is a pretrained universal phone recognizer for more than 2000 languages
dangvansam/viet-asr
VietASR - Vietnamese Automatic Speech Recognition
wenet-e2e/wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit
srvk/eesen
The official repository of the Eesen project