metadata

library_name: transformers
language:
  - zh
license: apache-2.0
base_model: openai/whisper-base
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - aimpower/mandarin_stutter_speech
metrics:
  - wer
model-index:
  - name: Whisper Base ZH - Dongim Lee
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: AImpower Mandarin Stutter Speech
          type: aimpower/mandarin_stutter_speech
          config: zh
          split: test
        metrics:
          - name: Wer
            type: wer
            value: 87.24489795918367

Whisper Base ZH - Dongim Lee

This model is a fine-tuned version of openai/whisper-base on the AImpower Mandarin Stutter Speech dataset. It achieves the following results on the evaluation set:

Loss: 0.4500
Wer: 87.2449

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: 500
training_steps: 4000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2036	2.0704	1000	0.3756	86.5816
0.0885	4.1408	2000	0.3903	86.2245
0.0367	6.2112	3000	0.4295	86.8878
0.0242	8.2816	4000	0.4500	87.2449

Framework versions

Transformers 4.44.2
Pytorch 2.5.0+cu121
Datasets 3.1.0
Tokenizers 0.19.1