metadata
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 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: validation[:1000]
args: pt
metrics:
- name: WER
type: wer
value: 4.816664144852979
- name: CER
type: cer
value: 1.6052355927195898
Whisper Large Portuguese
This model is a fine-tuned version of openai/whisper-large-v2 on the mozilla-foundation/common_voice_11_0 pt dataset. It achieves the following results on the evaluation set:
- WER: 4.816664144852979
- CER: 1.6052355927195898
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: 5e-06
- 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: 2000
- training_steps: 20000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 0.1051 | 1.24 | 1000 | 0.1501 | 5.1922 | 1.5979 |
| 0.0682 | 2.47 | 2000 | 0.1589 | 5.7523 | 1.8633 |
| 0.0489 | 3.71 | 3000 | 0.1631 | 5.3588 | 1.6819 |
| 0.0309 | 4.94 | 4000 | 0.1707 | 5.2831 | 1.6819 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2