Sagicc
/

whisper-medium-sr-yodas

Automatic Speech Recognition

Model card Files Files and versions

Metrics Training metrics Community

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: 7

Safetensors

Model size

0.8B params

Tensor type

F32

·

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

Collection including Sagicc/whisper-medium-sr-yodas

Whisper Serbian

Fine tuned Whisper on Serbian datasets • 4 items • Updated Jun 9, 2024 • 1