Whisper Medium Yodas

This model is a fine-tuned version of openai/whisper-medium on the multiple datasets.

Testing new dataset espnet/yodas

It achieves the following results on the evaluation set:

Loss: 0.1466
Wer Ortho: 0.1771
Wer: 0.0811

Downloads last month: 24

Safetensors

Model size

764M params

Tensor type

F32

Inference Examples

Automatic Speech Recognition

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.

Datasets used to train Sagicc/whisper-medium-sr-yodas

Collection including Sagicc/whisper-medium-sr-yodas

Whisper Serbian

Collection

Fine tuned Whisper on Serbian datasets • 4 items • Updated Jun 9