|
--- |
|
language: |
|
- pt |
|
license: apache-2.0 |
|
tags: |
|
- whisper-event |
|
- generated_from_trainer |
|
datasets: |
|
- mozilla-foundation/common_voice_11_0 |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: Whisper Large v2 Portuguese |
|
results: |
|
- task: |
|
name: Automatic Speech Recognition |
|
type: automatic-speech-recognition |
|
dataset: |
|
name: mozilla-foundation/common_voice_11_0 pt |
|
type: mozilla-foundation/common_voice_11_0 |
|
config: pt |
|
split: test |
|
args: pt |
|
metrics: |
|
- name: Wer |
|
type: wer |
|
value: 5.590020342630419 |
|
--- |
|
|
|
# Whisper Large V2 Portuguese 🇧🇷🇵🇹 |
|
|
|
Bem-vindo ao **whisper large-v2** para transcrição em português 👋🏻 |
|
|
|
Transcribe Portuguese audio to text with the highest precision. |
|
|
|
- Loss: 0.282 |
|
- Wer: 5.590 |
|
|
|
This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the [mozilla-foundation/common_voice_11](https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0) dataset. If you want a lighter model, you may be interested in [jlondonobo/whisper-medium-pt](https://huggingface.co/jlondonobo/whisper-medium-pt). It achieves faster inference with almost no difference in WER. |
|
|
|
### Comparable models |
|
Reported **WER** is based on the evaluation subset of Common Voice. |
|
| Model | WER | # Parameters | |
|
|--------------------------------------------------|:--------:|:------------:| |
|
| [jlondonobo/whisper-large-v2-pt](https://huggingface.co/jlondonobo/whisper-large-v2-pt) | **5.590** 🤗 | 1550M | |
|
| [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) | 6.300 | 1550M | |
|
| [jlondonobo/whisper-medium-pt](https://huggingface.co/jlondonobo/whisper-medium-pt) | 6.579 | 769M | |
|
| [jonatasgrosman/wav2vec2-large-xlsr-53-portuguese](https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-portuguese) | 11.310 | 317M | |
|
| [Edresson/wav2vec2-large-xlsr-coraa-portuguese](https://huggingface.co/Edresson/wav2vec2-large-xlsr-coraa-portuguese) | 20.080 | 317M | |
|
|
|
|
|
### Training hyperparameters |
|
We used the following hyperparameters for training: |
|
- `learning_rate`: 1e-05 |
|
- `train_batch_size`: 16 |
|
- `eval_batch_size`: 8 |
|
- `seed`: 42 |
|
- `gradient_accumulation_steps`: 2 |
|
- `total_train_batch_size`: 32 |
|
- `optimizer`: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- `lr_scheduler_type`: linear |
|
- `lr_scheduler_warmup_steps`: 500 |
|
- `training_steps`: 5000 |
|
- `mixed_precision_training`: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 0.0828 | 1.09 | 1000 | 0.1868 | 6.778 | |
|
| 0.0241 | 3.07 | 2000 | 0.2057 | 6.109 | |
|
| 0.0084 | 5.06 | 3000 | 0.2367 | 6.029 | |
|
| 0.0015 | 7.04 | 4000 | 0.2469 | 5.709 | |
|
| 0.0009 | 9.02 | 5000 | 0.2821 | 5.590 🤗| |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.0.dev0 |
|
- Pytorch 1.13.0+cu117 |
|
- Datasets 2.7.1.dev0 |
|
- Tokenizers 0.13.2 |
|
|
