tarun-bisht/wav2vec2-asr
wav2vec2 asr with transformers
This project helps convert spoken words into written text. It takes an audio recording or a live voice input and produces a transcription of what was said. This is useful for anyone who needs to quickly convert spoken content into a readable format, such as journalists, researchers, or meeting facilitators.
No commits in the last 6 months.
Use this if you need a way to automatically transcribe audio files or live speech into text.
Not ideal if you require real-time, highly accurate transcription for very specialized or noisy audio without prior language model training.
Stars
16
Forks
5
Language
Jupyter Notebook
License
—
Category
Last pushed
Oct 26, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/tarun-bisht/wav2vec2-asr"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
felixbur/nkululeko
Machine learning speaker characteristics
claritychallenge/clarity
Clarity Challenge toolkit - software for building Clarity Challenge systems
juanmc2005/diart
A python package to build AI-powered real-time audio applications
astorfi/3D-convolutional-speaker-recognition
:speaker: Deep Learning & 3D Convolutional Neural Networks for Speaker Verification
wq2012/awesome-diarization
A curated list of awesome Speaker Diarization papers, libraries, datasets, and other resources.