Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
np
whisper
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("aamoshdahal/whisper-small-nepali")
model = AutoModelForSpeechSeq2Seq.from_pretrained("aamoshdahal/whisper-small-nepali", device_map="auto")Quick Links
Whisper Small Nepali
This model is a fine-tuned version of openai/whisper-small on the Nepali Speech-to-Text Dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.4741
- Wer: 41.8257
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: Use OptimizerNames.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: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0121 | 9.6154 | 1000 | 0.3463 | 44.6216 |
| 0.0014 | 19.2308 | 2000 | 0.4206 | 42.2300 |
| 0.0001 | 28.8462 | 3000 | 0.4535 | 41.8706 |
| 0.0 | 38.4615 | 4000 | 0.4684 | 41.8482 |
| 0.0 | 48.0769 | 5000 | 0.4741 | 41.8257 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.1
- Tokenizers 0.21.0
- Downloads last month
- 12
Model tree for aamoshdahal/whisper-small-nepali
Base model
openai/whisper-smallDataset used to train aamoshdahal/whisper-small-nepali
Evaluation results
- Wer on Nepali Speech-to-Text Datasetself-reported41.826
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="aamoshdahal/whisper-small-nepali")