|
--- |
|
language: |
|
- zh |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
base_model: openai/whisper-tiny |
|
datasets: |
|
- mozilla-foundation/common_voice_16_1 |
|
model-index: |
|
- name: Whisper Tiny chinese - VingeNie |
|
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 chinese - VingeNie |
|
|
|
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Common Voice 16.1 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.0204 |
|
- Cer Ortho: 48.2903 |
|
- Cer: 37.8890 |
|
|
|
## 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-06 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 100 |
|
- training_steps: 500 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Cer Ortho | Cer | |
|
|:-------------:|:------:|:----:|:---------------:|:---------:|:-------:| |
|
| 2.027 | 0.1088 | 100 | 1.8566 | 58.8395 | 45.4613 | |
|
| 1.0547 | 0.2176 | 200 | 1.0853 | 50.8309 | 39.8595 | |
|
| 1.0003 | 0.3264 | 300 | 1.0360 | 47.7982 | 38.6397 | |
|
| 0.9744 | 0.4353 | 400 | 1.0224 | 48.7018 | 38.0597 | |
|
| 0.9318 | 0.5441 | 500 | 1.0204 | 48.2903 | 37.8890 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |
|
|
