metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- generated_from_trainer
datasets:
- common_voice_18_0
metrics:
- wer
model-index:
- name: whisper-large-v3-pt-3000h-3
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_18_0
type: common_voice_18_0
config: pt
split: None
args: pt
metrics:
- name: Wer
type: wer
value: 0.10419602818705957
whisper-large-v3-pt-3000h-3
This model is a fine-tuned version of openai/whisper-large-v3 on the common_voice_18_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2671
- Wer: 0.1042
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- 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: 1000
- num_epochs: 10.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1388 | 0.9996 | 691 | 0.1501 | 0.1074 |
| 0.108 | 1.9993 | 1382 | 0.1619 | 0.1153 |
| 0.091 | 2.9989 | 2073 | 0.1697 | 0.1124 |
| 0.0461 | 4.0 | 2765 | 0.1764 | 0.1120 |
| 0.0264 | 4.9996 | 3456 | 0.2024 | 0.1133 |
| 0.0203 | 5.9993 | 4147 | 0.2200 | 0.1099 |
| 0.0129 | 6.9989 | 4838 | 0.2277 | 0.1114 |
| 0.0091 | 8.0 | 5530 | 0.2552 | 0.1067 |
| 0.0063 | 8.9996 | 6221 | 0.2565 | 0.1054 |
| 0.0019 | 9.9964 | 6910 | 0.2671 | 0.1042 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.4.0+cu124
- Datasets 2.18.1.dev0
- Tokenizers 0.19.1