YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
swadeshi_hindiwav2vec2asr/ is a Hindi speech recognition model which is a fine tuned version of the theainerd/Wav2Vec2-large-xlsr-hindi model. The model achieved a Word Error Rate of 0.738 when trained with 12 Hours of MUCS data with 30 epochs and given a batch size of 12.
- Downloads last month
- 2