metadata

library_name: transformers
language:
  - yue
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_15_0
  - mozilla-foundation/common_voice_16_1
metrics:
  - wer
model-index:
  - name: Whisper Small Canontese X v2
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 16.1
          type: mozilla-foundation/common_voice_15_0
          config: zh-HK
          split: None
          args: 'config: zh-HK, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 59.33048433048433
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 15.0
          type: mozilla-foundation/common_voice_16_1
        metrics:
          - name: Wer
            type: wer
            value: 59.33048433048433

Whisper Small Canontese X v2

This model is a fine-tuned version of openai/whisper-small on the Common Voice 16.1 and the Common Voice 15.0 datasets. It achieves the following results on the evaluation set:

Loss: 0.2720
Wer: 59.3305

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: 8
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: 3000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2939	0.7918	1000	0.3060	65.9188
0.1498	1.5835	2000	0.2803	61.6809
0.0662	2.3753	3000	0.2720	59.3305

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.0.0
Tokenizers 0.19.1