---
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: 0.2344
- Cer: 12.5425

## 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: 976
- training_steps: 9760
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Cer     |
|:-------------:|:-------:|:----:|:---------------:|:-------:|
| 1.1066        | 0.9980  | 488  | 1.2078          | 49.8428 |
| 0.3421        | 1.9959  | 976  | 0.5032          | 26.3703 |
| 0.1775        | 2.9939  | 1464 | 0.3401          | 17.7012 |
| 0.1069        | 3.9918  | 1952 | 0.2920          | 18.6536 |
| 0.0719        | 4.9898  | 2440 | 0.2630          | 15.3975 |
| 0.0467        | 5.9877  | 2928 | 0.2507          | 15.8182 |
| 0.0302        | 6.9857  | 3416 | 0.2454          | 16.1523 |
| 0.0217        | 7.9836  | 3904 | 0.2407          | 14.2000 |
| 0.0157        | 8.9816  | 4392 | 0.2387          | 13.9053 |
| 0.0105        | 9.9796  | 4880 | 0.2373          | 14.6473 |
| 0.0066        | 10.9775 | 5368 | 0.2338          | 15.3628 |
| 0.005         | 11.9755 | 5856 | 0.2352          | 14.5040 |
| 0.0038        | 12.9734 | 6344 | 0.2321          | 14.1411 |
| 0.0035        | 13.9714 | 6832 | 0.2348          | 12.9644 |
| 0.0025        | 14.9693 | 7320 | 0.2335          | 13.4348 |
| 0.0022        | 15.9673 | 7808 | 0.2337          | 13.8186 |
| 0.0019        | 16.9652 | 8296 | 0.2345          | 13.7897 |
| 0.0018        | 17.9632 | 8784 | 0.2347          | 12.8430 |
| 0.0016        | 18.9611 | 9272 | 0.2341          | 13.1724 |
| 0.0016        | 19.9591 | 9760 | 0.2344          | 12.5425 |


### Framework versions

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