metadata

language:
  - sv
  - 'no'
  - da
license: apache-2.0
tags:
  - whisper-event
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
  - babelbox/babelbox_voice
  - NbAiLab/NST
  - NbAiLab/NPSC
  - google/fleurs
metrics:
  - wer
model-index:
  - name: Whisper Medium Nordic
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: mozilla-foundation/common_voice_11_0
          type: mozilla-foundation/common_voice_11_0
          config: sv-SE
          split: test
        metrics:
          - name: Wer
            type: wer
            value: 11.31
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: mozilla-foundation/common_voice_11_0
          type: mozilla-foundation/common_voice_11_0
          config: da
          split: test
        metrics:
          - name: Wer
            type: wer
            value: 14.86
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: mozilla-foundation/common_voice_11_0
          type: mozilla-foundation/common_voice_11_0
          config: nn-NO
          split: test
        metrics:
          - name: Wer
            type: wer
            value: 37.02

Whisper Medium Nordic

This model is a fine-tuned version of openai/whisper-medium on the mozilla-foundation/common_voice_11_0 (sv-SE, da, nn-NO), the babelbox/babelbox_voice (Swedish radio), the NbAiLab/NST (Norwegian radio), the NbAiLab/NPSC (Norwegian parliament) and the google/fleurs (sv_se, da_dk, nb_no) datasets. The goal is to leverage transfer learning across Nordic languages, which have strong similarities.

It achieves the following results on the common voice Swedish test set:

Loss: 0.2129
Wer: 11.3079

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Please note that a bug during training prevented us from evaluating WER correctly. Validation loss suggests we started overfitting after 5000/6000 steps.

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 3e-06
train_batch_size: 32
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
training_steps: 10000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.3056	0.1	1000	0.2670	99.9221
0.16	0.2	2000	0.2322	99.6640
0.1309	0.3	3000	0.2152	98.9759
0.097	0.4	4000	0.2112	100.0
0.091	0.5	5000	0.2094	99.7312
0.1098	0.6	6000	0.2098	98.6077
0.0637	0.7	7000	0.2148	98.4625
0.0718	0.8	8000	0.2151	99.8710
0.0517	0.9	9000	0.2175	97.2342
0.0465	1.0	10000	0.2129	96.3552

Framework versions

Transformers 4.26.0.dev0
Pytorch 1.13.1+cu117
Datasets 2.7.1.dev0
Tokenizers 0.13.2