metadata
license: apache-2.0
language:
- eu
tags:
- whisper-event
- generated_from_trainer
datasets:
- common_voice_11_0
metrics:
- wer
model-index:
- name: openai/whisper-small
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_11_0
type: common_voice_11_0
config: eu
split: test
args: eu
metrics:
- name: Wer
type: wer
value: 19.766305675433596
openai/whisper-small
This model is a fine-tuned version of openai/whisper-small on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4485
- Wer: 19.7663
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: 64
- eval_batch_size: 32
- 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: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.048 | 4.04 | 1000 | 0.3402 | 21.7816 |
| 0.0047 | 9.03 | 2000 | 0.3862 | 20.1694 |
| 0.0012 | 14.02 | 3000 | 0.4221 | 19.7419 |
| 0.0008 | 19.02 | 4000 | 0.4411 | 19.7174 |
| 0.0006 | 24.01 | 5000 | 0.4485 | 19.7663 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2