Epoch	Training Loss	Validation Loss	Word Error Rate (WER)
1	0.9888	2.4769	76.82%
2	0.6309	2.2758	100.69%
3	0.3404	2.2675	111.08%
4	0.3789	2.2711	167.74%
5	0.1815	2.4075	132.40%
6	0.1382	2.3016	182.50%

Safetensors

Model size

1.54B params

Tensor type

F32

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for AwaazSehat/shalamar-finetuned-whisper-large-v3

Base model

Finetuned

(513)

this model