Belle-whisper-large-v3-zh
transcriber = pipeline( "automatic-speech-recognition", model="BELLE-2/Belle-whisper-large-v3-zh" ).
audio → text · made by BELLE-2 Group // Be Everyone's Large Language model Engine
Sold by
Nobody in the catalogue publishes a price for this yet.
About
Belle-whisper-large-v3-zh — a text model from BELLE-2 Group // Be Everyone's Large Language model Engine.
It takes audio and returns text. It was published in March 2024. The catalogue files it under transcribe. Its weights are published under APACHE-2.0, so you may run it on your own machine, or buy it from whoever serves it cheapest.
Every current figure
- Maker
- BELLE-2 Group // Be Everyone's Large Language model Engine
- Register
- model
- Takes
- audio
- Returns
- text
- Published
- March 2024
- Parameters
- 1.5 billion · read from its own weights
- Licence
- apache-2.0
Known as 1 name
BELLE-2/Belle-whisper-large-v3-zh