metadata
language:
- gn
license: apache-2.0
base_model: openai/whisper-base
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_16_1
metrics:
- wer
model-index:
- name: Common Voice 16 - Guarani
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 16
type: mozilla-foundation/common_voice_16_1
config: gn
split: None
args: gn
metrics:
- name: Wer
type: wer
value: 56.50474595198214
Common Voice 16 - Guarani
This model is a fine-tuned version of openai/whisper-base on the Common Voice 16 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5052
- Wer: 56.5047
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 500
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 4.2519 | 0.0991 | 100 | 2.0016 | 176.2144 |
| 1.9569 | 0.1982 | 200 | 1.0866 | 92.1273 |
| 1.3814 | 0.2973 | 300 | 0.8375 | 77.2194 |
| 1.0866 | 0.3964 | 400 | 0.7128 | 69.4026 |
| 0.8892 | 0.4955 | 500 | 0.6427 | 68.7326 |
| 0.7668 | 0.5946 | 600 | 0.5942 | 65.7175 |
| 0.698 | 0.6938 | 700 | 0.5732 | 60.9715 |
| 0.593 | 0.7929 | 800 | 0.5278 | 57.5656 |
| 0.5585 | 0.8920 | 900 | 0.5330 | 60.2457 |
| 0.5199 | 0.9911 | 1000 | 0.5052 | 56.5047 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1