metadata

language:
  - zh
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - whucedar/datasets_stt_1
metrics:
  - wer
model-index:
  - name: zh-CN-model-medium-1 - whucedar
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: datasets_stt_1
          type: whucedar/datasets_stt_1
          args: 'config: zh, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 188.47926267281105

zh-CN-model-medium-1 - whucedar

This model is a fine-tuned version of openai/whisper-medium on the datasets_stt_1 dataset. It achieves the following results on the evaluation set:

Loss: 0.1323
Wer: 188.4793

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: 16
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: 50
training_steps: 500
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0241	1.5873	100	0.1363	158.9862
0.0042	3.1746	200	0.1312	239.6313
0.0043	4.7619	300	0.1316	215.2074
0.0013	6.3492	400	0.1312	203.6866
0.0006	7.9365	500	0.1323	188.4793

Framework versions

Transformers 4.42.3
Pytorch 2.3.1+cu118
Datasets 2.20.0
Tokenizers 0.19.1