|
--- |
|
library_name: transformers |
|
language: |
|
- en |
|
license: apache-2.0 |
|
base_model: openai/whisper-tiny |
|
tags: |
|
- hf-asr-leaderboard |
|
- generated_from_trainer |
|
datasets: |
|
- chinese_english_R_fa |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: Whisper tiny Chinese |
|
results: |
|
- task: |
|
name: Automatic Speech Recognition |
|
type: automatic-speech-recognition |
|
dataset: |
|
name: Chinese English 'R' Phonemes |
|
type: chinese_english_R_fa |
|
args: 'config: default, split: test' |
|
metrics: |
|
- name: Wer |
|
type: wer |
|
value: 14.00504686373468 |
|
--- |
|
|
|
<!-- 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 |
|
|
|
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Chinese English 'R' Phonemes dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3367 |
|
- Wer: 14.0050 |
|
|
|
## 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: 2 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- training_steps: 3000 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:------:|:----:|:---------------:|:-------:| |
|
| 0.1284 | 1.5038 | 1000 | 0.3222 | 14.5818 | |
|
| 0.0295 | 3.0075 | 2000 | 0.3241 | 13.9149 | |
|
| 0.0027 | 4.5113 | 3000 | 0.3367 | 14.0050 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.48.3 |
|
- Pytorch 2.6.0+cu124 |
|
- Datasets 3.4.1 |
|
- Tokenizers 0.21.1 |
|
|
