README.md

metadata

language:
  - zh
license: apache-2.0
base_model: ZhihCheng/whisper-tiny-zh
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: Whisper tiny zh v2
    results: []
datasets:
  - ZhihCheng/Motor_jargon_dataset

Whisper tiny zh v2

This model is a fine-tuned version of ZhihCheng/whisper-tiny-zh on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0257
• Wer: 8.1081

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: 25
• training_steps: 200
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4201	0.62	50	0.2035	72.9730
0.1236	1.25	100	0.0640	31.5315
0.0849	1.88	150	0.0320	9.9099
0.0388	2.5	200	0.0257	8.1081

Framework versions

• Transformers 4.38.0.dev0
• Pytorch 2.2.0a0+6a974be
• Datasets 2.16.1
• Tokenizers 0.15.1