82 lines
2.0 KiB
Markdown
82 lines
2.0 KiB
Markdown
|
---
|
||
|
|
library_name: transformers
|
||
|
|
language:
|
||
|
|
- es
|
||
|
|
license: apache-2.0
|
||
|
|
base_model: openai/whisper-small
|
||
|
|
tags:
|
||
|
|
- generated_from_trainer
|
||
|
|
datasets:
|
||
|
|
- ylacombe/google-chilean-spanish
|
||
|
|
metrics:
|
||
|
|
- wer
|
||
|
|
model-index:
|
||
|
|
- name: Whisper Small ES-CL - Roberto Castro-Vexler
|
||
|
|
results:
|
||
|
|
- task:
|
||
|
|
name: Automatic Speech Recognition
|
||
|
|
type: automatic-speech-recognition
|
||
|
|
dataset:
|
||
|
|
name: OpenSLR Chilean Spanish
|
||
|
|
type: ylacombe/google-chilean-spanish
|
||
|
|
args: 'config: es-cl, split: test'
|
||
|
|
metrics:
|
||
|
|
- name: Wer
|
||
|
|
type: wer
|
||
|
|
value: 5.930960948953752
|
||
|
|
---
|
||
|
|
|
||
|
|
<!-- 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 ES-CL - Roberto Castro-Vexler
|
||
|
|
|
||
|
|
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the OpenSLR Chilean Spanish dataset.
|
||
|
|
It achieves the following results on the evaluation set:
|
||
|
|
- Loss: 0.1552
|
||
|
|
- Wer: 5.9310
|
||
|
|
|
||
|
|
## 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: 16
|
||
|
|
- eval_batch_size: 8
|
||
|
|
- seed: 42
|
||
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
||
|
|
- lr_scheduler_type: linear
|
||
|
|
- lr_scheduler_warmup_steps: 500
|
||
|
|
- training_steps: 4000
|
||
|
|
- mixed_precision_training: Native AMP
|
||
|
|
|
||
|
|
### Training results
|
||
|
|
|
||
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
||
|
|
|:-------------:|:-------:|:----:|:---------------:|:------:|
|
||
|
|
| 0.0038 | 8.6207 | 1000 | 0.1381 | 6.1975 |
|
||
|
|
| 0.0002 | 17.2414 | 2000 | 0.1466 | 5.8510 |
|
||
|
|
| 0.0001 | 25.8621 | 3000 | 0.1528 | 5.9709 |
|
||
|
|
| 0.0001 | 34.4828 | 4000 | 0.1552 | 5.9310 |
|
||
|
|
|
||
|
|
|
||
|
|
### Framework versions
|
||
|
|
|
||
|
|
- Transformers 4.45.2
|
||
|
|
- Pytorch 2.4.1+cu121
|
||
|
|
- Datasets 3.0.1
|
||
|
|
- Tokenizers 0.20.1
|