yl4579/AuxiliaryASR
Joint CTC-S2S Phoneme-level ASR for Voice Conversion and TTS (Text-Mel Alignment)
This project helps researchers and developers in speech technology fine-tune or train an Automatic Speech Recognition (ASR) model specifically for voice conversion and text-to-speech applications. It takes audio recordings with corresponding text labels and speaker information as input, producing a specialized ASR model that accurately aligns phonemes with audio. This is ideal for those working on synthesizing realistic speech or transforming voices.
125 stars. No commits in the last 6 months.
Use this if you need to train a phoneme-level ASR model to precisely align audio with text for advanced voice conversion or text-to-speech systems.
Not ideal if you're looking for a general-purpose, off-the-shelf ASR solution for transcribing speech or command and control applications.
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....
dangvansam/viet-asr
VietASR - Vietnamese Automatic Speech Recognition
wenet-e2e/wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit
xinjli/allosaurus
Allosaurus is a pretrained universal phone recognizer for more than 2000 languages
srvk/eesen
The official repository of the Eesen project