metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - common_voice_11_0
metrics:
  - wer
model-index:
  - name: whisper-large-zh-cv11
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice_11_0
          type: common_voice_11_0
          config: zh-CN
          split: validation[:1000]
          args: zh-CN
        metrics:
          - name: Wer
            type: wer
            value: 52.307692307692314

whisper-large-zh-cv11

This model is a fine-tuned version of openai/whisper-large-v2 on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:

Loss: 0.2501
Wer: 52.3077
Cer: 8.9573

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: 5e-06
train_batch_size: 16
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 2000
training_steps: 20000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.3314	0.83	1000	0.2110	65.7014	10.8047
0.2747	1.66	2000	0.2005	58.1900	9.4191
0.1989	2.49	3000	0.1983	56.1991	9.0939
0.1142	3.31	4000	0.2076	55.0226	9.1589
0.0747	4.14	5000	0.2131	56.3801	9.0483
0.0709	4.97	6000	0.2165	54.6606	8.9768
0.0432	5.8	7000	0.2222	54.0271	8.9508
0.0261	6.63	8000	0.2299	54.4796	9.0353
0.0152	7.46	9000	0.2290	52.7602	8.8076
0.0054	8.28	10000	0.2435	51.6742	8.5279
0.0028	9.11	11000	0.2421	53.0317	8.9833
0.0045	9.94	12000	0.2462	52.9412	8.7751
0.0016	10.77	13000	0.2501	52.3077	8.9573

Framework versions

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