|
--- |
|
language: |
|
- zh |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- hf-asr-leaderboard |
|
- generated_from_trainer |
|
datasets: |
|
- mozilla-foundation/common_voice_15_0 |
|
base_model: openai/whisper-small |
|
model-index: |
|
- name: Whisper small TW - AlanDlink |
|
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 small TW - AlanDlink |
|
|
|
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 15.0 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2175 |
|
|
|
## 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: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- training_steps: 8000 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.2151 | 1.33 | 1000 | 2.1197 | |
|
| 0.5107 | 2.67 | 2000 | 0.4872 | |
|
| 0.294 | 4.0 | 3000 | 0.2780 | |
|
| 0.229 | 5.33 | 4000 | 0.2428 | |
|
| 0.2193 | 6.67 | 5000 | 0.2278 | |
|
| 0.2292 | 8.0 | 6000 | 0.2213 | |
|
| 0.2288 | 9.33 | 7000 | 0.2184 | |
|
| 0.2065 | 10.67 | 8000 | 0.2175 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.7.1 |
|
- Transformers 4.36.2 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.16.0 |
|
- Tokenizers 0.15.0 |
