metadata
base_model: openai/whisper-large-v3
datasets:
- b-brave/speech_disorders_voice
language:
- it
library_name: peft
license: apache-2.0
metrics:
- wer
tags:
- generated_from_trainer
model-index:
- name: Whisper Large v3
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: b-brave/speech_disorders_voice
type: b-brave/speech_disorders_voice
config: default
split: train
args: default
metrics:
- type: wer
value: 23.517382413087933
name: Wer
Whisper Large v3
This model is a fine-tuned version of openai/whisper-large-v3 on the b-brave/speech_disorders_voice dataset. It achieves the following results on the evaluation set:
- Loss: 0.3055
- Wer: 23.5174
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: 0.001
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 128
- training_steps: 256
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.3683 | 0.9481 | 64 | 0.3394 | 19.8364 |
| 0.1165 | 1.8963 | 128 | 0.3326 | 15.3374 |
| 0.0332 | 2.8444 | 192 | 0.3112 | 19.6319 |
| 0.013 | 3.7926 | 256 | 0.3055 | 23.5174 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.2.0
- Datasets 2.21.0
- Tokenizers 0.19.1