# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("therealbee/whisper-finetuned")
model = AutoModelForSpeechSeq2Seq.from_pretrained("therealbee/whisper-finetuned")Quick Links
whisper-finetuned
This model is a fine-tuned version of MKAlbani/whisper-small-ha on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2252
- Wer: 13.5586
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: 16
- 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: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2256 | 0.1989 | 500 | 0.2817 | 16.8934 |
| 0.175 | 0.3978 | 1000 | 0.2252 | 13.5586 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
- Downloads last month
- 2
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="therealbee/whisper-finetuned")