juliuskunze/speechless

Speech-to-text based on wav2letter built for transfer learning

45
/ 100
Emerging

This project helps convert spoken words into text. You input audio recordings, and it outputs the transcribed text. It's designed for researchers, linguists, or anyone needing to train custom speech-to-text models, especially for different languages or specific accents, and who can work with Python.

No commits in the last 6 months.

Use this if you need to train a specialized speech recognition model from scratch or adapt an existing one to a new language or domain using your own audio data.

Not ideal if you're looking for a simple, out-of-the-box speech-to-text service without needing to train or fine-tune models yourself.

speech-recognition linguistics audio-transcription machine-learning-research language-model-training
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

98

Forks

25

Language

Python

License

MIT

Last pushed

Oct 21, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/juliuskunze/speechless"

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