---
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: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# Whisper Tiny Hakka Condenser

This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the HAT ASR Aligned dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0945
- Cer: 4.1693

## 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: 488
- training_steps: 4880
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Cer     |
|:-------------:|:------:|:----:|:---------------:|:-------:|
| 0.5588        | 0.9980 | 488  | 0.5489          | 24.8653 |
| 0.1837        | 1.9959 | 976  | 0.1979          | 8.1316  |
| 0.109         | 2.9939 | 1464 | 0.1409          | 5.4419  |
| 0.0765        | 3.9918 | 1952 | 0.1202          | 4.8720  |
| 0.0524        | 4.9898 | 2440 | 0.1075          | 4.2675  |
| 0.0391        | 5.9877 | 2928 | 0.1009          | 4.2479  |
| 0.0272        | 6.9857 | 3416 | 0.0984          | 4.4629  |
| 0.0232        | 7.9836 | 3904 | 0.0954          | 4.0791  |
| 0.0196        | 8.9816 | 4392 | 0.0948          | 3.9046  |
| 0.015         | 9.9796 | 4880 | 0.0945          | 4.1693  |


### Framework versions

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