Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
English
whisper
Generated from Trainer
# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("navin-kumar-j/whisper-base-en-w-pcd-10-4")
model = AutoModelForSpeechSeq2Seq.from_pretrained("navin-kumar-j/whisper-base-en-w-pcd-10-4")Quick Links
Whisper Base English with Phone Control Data - Navin Kumar J
This model is a fine-tuned version of openai/whisper-base.en on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0133
- Wer: 0.0046
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 8
- 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: linear
- lr_scheduler_warmup_steps: 10
- training_steps: 200
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0438 | 0.9091 | 40 | 0.0558 | 0.0107 |
| 0.002 | 1.8182 | 80 | 0.0117 | 0.0046 |
| 0.0 | 2.7273 | 120 | 0.0123 | 0.0031 |
| 0.0 | 3.6364 | 160 | 0.0132 | 0.0046 |
| 0.0 | 4.5455 | 200 | 0.0133 | 0.0046 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.7.0+cu126
- Datasets 3.5.0
- Tokenizers 0.21.1
- Downloads last month
- 3
Model tree for navin-kumar-j/whisper-base-en-w-pcd-10-4
Base model
openai/whisper-base.en
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="navin-kumar-j/whisper-base-en-w-pcd-10-4")