RF5/transfusion-asr
Transcribing Speech with Multinomial Diffusion, training code and models.
This project offers a powerful tool for converting spoken audio into written text. You provide audio files (like recordings of meetings or interviews), and it outputs a highly accurate text transcription. It is designed for researchers, data scientists, or anyone working with large volumes of speech data who needs to automatically generate transcripts.
No commits in the last 6 months.
Use this if you need to transcribe spoken language from audio files into text with high accuracy, especially for research or data analysis purposes.
Not ideal if you're looking for a simple, off-the-shelf transcription service without any technical setup or if your main goal is real-time transcription.
Stars
80
Forks
5
Language
Python
License
—
Category
Last pushed
Sep 27, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/RF5/transfusion-asr"
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