Hugging Face's logo

jethrowang
/
webcam_topline-whisper-medium

TensorBoard
Safetensors
Chinese
whisper
Generated from Trainer
Model card Files Metrics Community
webcam_topline-whisper-medium / README.md
jethrowang's picture
jethrowang
End of training
292c94e verified
preview code
|
raw
history blame contribute delete
1.76 kB
metadata
language:
  - zh
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - generated_from_trainer
datasets:
  - formospeech/hat_asr_aligned
model-index:
  - name: Whisper Medium Hakka Webcam
    results: []

Whisper Medium Hakka Webcam

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

  • Loss: 0.0220
  • Cer: 0.8172

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: 32
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 1521
  • training_steps: 15215
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Cer
0.0403 0.9997 3043 0.0423 1.8390
0.0141 1.9993 6086 0.0286 1.1443
0.0059 2.9990 9129 0.0244 0.9744
0.0028 3.9987 12172 0.0221 0.8796
0.0007 4.9984 15215 0.0220 0.8172

Framework versions

  • Transformers 4.42.3
  • Pytorch 2.3.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1