metadata

license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_9_0
metrics:
  - wer
model-index:
  - name: yt-special-batch4
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: mozilla-foundation/common_voice_9_0 id
          type: mozilla-foundation/common_voice_9_0
          config: id
          split: train
          args: id
        metrics:
          - name: Wer
            type: wer
            value: 28.23428448830723

yt-special-batch4

This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_9_0 id dataset. It achieves the following results on the evaluation set:

Loss: 3.6844
Wer: 28.2343

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 4
eval_batch_size: 2
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 5000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
125.5137	0.79	1000	129.9009	149.0002
67.2464	1.59	2000	59.3172	298.8672
34.7799	2.38	3000	28.5244	134.9260
13.5007	3.17	4000	12.5162	51.1457
7.3781	3.97	5000	3.6844	28.2343

Framework versions

Transformers 4.31.0.dev0
Pytorch 2.0.1+cu117
Datasets 2.13.1
Tokenizers 0.13.3