lucadellalib/ts-asr

Target speaker automatic speech recognition (TS-ASR)

29
/ 100
Experimental

This project offers tools to build advanced speech recognition systems that can isolate and transcribe the speech of a specific person, even in noisy conversations. It takes mixed audio recordings and information about the target speaker, producing a clear transcript of only that speaker's words. It is designed for speech AI researchers and engineers developing next-generation voice technologies.

No commits in the last 6 months.

Use this if you are a researcher or engineer working on automatic speech recognition and need to train models capable of transcribing a specific speaker's voice in multi-speaker environments.

Not ideal if you are looking for a ready-to-use application to transcribe audio files without delving into model training and development.

speech-recognition-research voice-AI-development audio-processing-engineering machine-learning-for-speech speaker-diarization
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 16 / 25

How are scores calculated?

Stars

12

Forks

6

Language

Python

License

Last pushed

Oct 14, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/lucadellalib/ts-asr"

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