Roy229/filesystem_fetch_huggingface_3144_mdl_whisper-base

Whisper base Model Card

Model Summary

Whisper is a Transformer based encoder-decoder model, also referred to as a sequence-to-sequence model. It was trained on 680k hours of labelled speech data annotated using large-scale weak supervision.

Intended Uses

The model is intended for research and downstream task fine-tuning. Application developers should assess suitability for their specific use case before deployment.

Limitations

The model may produce biased or incorrect outputs. It was not fine-tuned for production use.

License

The model is licensed under the Apache-2.0 license.

tags: audit-verified