Open-Speech-EkStep/vakyansh-wav2vec2-experimentation

Repository containing experimentation platform on how to train, infer on wav2vec2 models.

46
/ 100
Emerging

This project helps developers and researchers working on speech technology to build and customize speech-to-text models for Indic languages. It takes audio recordings and corresponding text transcripts as input and outputs trained models that can convert new speech into written text. This is designed for machine learning engineers or AI researchers specializing in speech recognition.

No commits in the last 6 months.

Use this if you need to train, fine-tune, or perform inference with Wav2Vec2 models for speech recognition, especially for Indic languages.

Not ideal if you are looking for an out-of-the-box, end-user speech-to-text application without needing to train or fine-tune models.

speech-recognition natural-language-processing machine-learning-engineering AI-research indic-languages
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

88

Forks

40

Language

Python

License

MIT

Last pushed

Sep 22, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/Open-Speech-EkStep/vakyansh-wav2vec2-experimentation"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.