README.md

metadata

language:
  - zh
license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_trainer
datasets:
  - formospeech/hat_asr_aligned
model-index:
  - name: Whisper Tiny Hakka Condenser
    results: []

Whisper Tiny Hakka Condenser

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

• eval_loss: 0.0505
• eval_cer: 2.4343
• eval_runtime: 597.3234
• eval_samples_per_second: 7.632
• eval_steps_per_second: 0.239
• step: 0

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: 64
• eval_batch_size: 32
• 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: 15210
• mixed_precision_training: Native AMP

Framework versions

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