|
--- |
|
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 Simulated Webcam |
|
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 Simulated Webcam |
|
|
|
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: 0.1319 |
|
- Cer: 7.3572 |
|
|
|
## 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: 0.0001 |
|
- 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 | |
|
|:-------------:|:------:|:----:|:---------------:|:-------:| |
|
| 0.2061 | 0.9980 | 488 | 0.3095 | 30.6829 | |
|
| 0.1014 | 1.9959 | 976 | 0.2149 | 16.2991 | |
|
| 0.0486 | 2.9939 | 1464 | 0.1858 | 15.3582 | |
|
| 0.0243 | 3.9918 | 1952 | 0.1723 | 14.7074 | |
|
| 0.0115 | 4.9898 | 2440 | 0.1626 | 12.7598 | |
|
| 0.0046 | 5.9877 | 2928 | 0.1542 | 9.6054 | |
|
| 0.0016 | 6.9857 | 3416 | 0.1437 | 8.7997 | |
|
| 0.0006 | 7.9836 | 3904 | 0.1355 | 9.0378 | |
|
| 0.0004 | 8.9816 | 4392 | 0.1315 | 7.8473 | |
|
| 0.0004 | 9.9796 | 4880 | 0.1319 | 7.3572 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.3 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
