Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Italian
whisper
hf-asr-leaderboard
Generated from Trainer
# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("SaladSlayer00/another_local")
model = AutoModelForSpeechSeq2Seq.from_pretrained("SaladSlayer00/another_local", device_map="auto")Quick Links
Whisper Small IT
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5372
- Wer: 130.3266
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: 16
- eval_batch_size: 8
- 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: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1972 | 1.6 | 500 | 0.4266 | 105.1927 |
| 0.033 | 3.19 | 1000 | 0.4507 | 209.0820 |
| 0.0167 | 4.79 | 1500 | 0.4738 | 96.0643 |
| 0.0052 | 6.39 | 2000 | 0.4948 | 143.7616 |
| 0.0035 | 7.99 | 2500 | 0.5144 | 126.8133 |
| 0.0047 | 9.58 | 3000 | 0.5273 | 133.8966 |
| 0.0033 | 11.18 | 3500 | 0.5349 | 137.8580 |
| 0.0026 | 12.78 | 4000 | 0.5372 | 130.3266 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 12
Model tree for SaladSlayer00/another_local
Base model
openai/whisper-small
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="SaladSlayer00/another_local")