FineTuned wav2vec2 large 960H lv60 self pre-trained facebook model on 72 Hours of MI Diaries Data
WER 13 % -> 9.7% on 20 min test set of MI Diaries audio clips (https://mi-diaries.org/)
Usage
model = Wav2Vec2ForCTC.from_pretrained("caurdy/wav2vec2-large-960h-lv60-self_MIDIARIES_72H_FT")
processor = Wav2Vec2Processor.from_pretrained("caurdy/wav2vec2-large-960h-lv60-self_MIDIARIES_72H_FT")
- Downloads last month
- 0
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.