metadata
language:
- it
license: apache-2.0
tags:
- whisper-event
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: Whisper tiny Italian - Mattia Surricchio
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_11_0
config: it
split: test
args: it
metrics:
- name: Wer
type: wer
value: 38.08739102700404
Whisper tiny Italian - Mattia Surricchio
This model is a fine-tuned version of openai/whisper-tiny on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.6699
- Wer: 38.0874
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: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.9004 | 0.2 | 100 | 0.8327 | 44.9534 |
| 0.6534 | 0.4 | 200 | 0.7341 | 41.3160 |
| 0.6727 | 0.6 | 300 | 0.6988 | 39.5871 |
| 0.4996 | 0.8 | 400 | 0.6766 | 38.6582 |
| 0.6236 | 1.0 | 500 | 0.6699 | 38.0874 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.11.0
- Datasets 2.7.1.dev0
- Tokenizers 0.12.1