Finnish-NLP
/

whisper-large-finnish-v3

Automatic Speech Recognition

speech-recognition

Eval Results (legacy)

Model card Files Files and versions

Metrics Training metrics Community

This is our improved Whisper v3 model that is now finetuned from OpenAI Whisper Large V3

We improve from our previously finetuned Whisper V2 model in the following mannerhttps://huggingface.co/Finnish-NLP/whisper-large-v2-finnish

CV11 (Common Voice 11 test set) WER (Word error rate) 10.42 --> 8.23

Fleurs (A speech recognition test set by Google) WER (Word error rate) 10.20 --> 8.21

Model was trained on Nvidia RTX4080 for 32k steps with batch size 8, gradient accumulation 2

Original OpenAI Whisper Large V3

- CV11 - WER: 14.81 - WER NORMALIZED: 10.82 - CER: 2.7 - CER NORMALIZED: 2.07

Fleurs
- WER: 12.04
- WER NORMALIZED: 9.63
- CER: 2.48
- CER NORMALIZED: 3.64

After Finetuning with Finnish data our V3 got these scores on the test set:

@14000 finetuning steps
- CV11
  - WER: 11.36
  - WER NORMALIZED: 8.31
  - CER: 1.93
  - CER NORMALIZED: 1.48
- Fleurs
  - WER: 10.2
  - WER NORMALIZED: 8.56
  - CER: 2.26
  - CER NORMALIZED: 3.54
@32000 finetuning steps
- CV11
  - WER: 11.47
  - WER NORMALIZED: 8.23
  - CER: 1.91
  - CER NORMALIZED: 1.43
- Fleurs
  - WER: 10.1
  - WER NORMALIZED: 8.21
  - CER: 2.2
  - CER NORMALIZED: 3.23

Downloads last month: 1,006

Safetensors

Model size

2B params

Tensor type

F16

·

Model tree for Finnish-NLP/whisper-large-finnish-v3

Finetunes

Quantizations

Dataset used to train Finnish-NLP/whisper-large-finnish-v3

Spaces using Finnish-NLP/whisper-large-finnish-v3 2

Collection including Finnish-NLP/whisper-large-finnish-v3

Finnish Whisper speech recognition

Whisper models finetuned for Finnish in various formats • 7 items • Updated Dec 31, 2024 • 2

Evaluation results

Wer on Common Voice 11.0
test set self-reported

8.230
Cer on Common Voice 11.0
test set self-reported

1.430
Wer on FLEURS
test set self-reported

8.210
Cer on FLEURS
test set self-reported

3.230