metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-small
tags:
- whisper-event
- generated_from_trainer
datasets:
- audiofolder
metrics:
- wer
model-index:
- name: openai/whisper-small
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: audiofolder
type: audiofolder
config: default
split: validation
args: default
metrics:
- type: wer
value: 55.43576297850026
name: Wer
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: mozilla-foundation/common_voice_11_0
type: mozilla-foundation/common_voice_11_0
config: en
split: test
metrics:
- type: wer
value: 85.75
name: WER
openai/whisper-small
This model is a fine-tuned version of openai/whisper-small on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.1091
- Wer: 55.4358
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: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 100
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
1.7682 | 0.5 | 50 | 1.8436 | 32.0993 |
0.5702 | 1.01 | 100 | 1.1091 | 55.4358 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.4.0+cu121
- Datasets 3.3.2
- Tokenizers 0.21.0