Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
English
whisper
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("Dev372/HarshDev-whisper-base-English_2000")
model = AutoModelForSpeechSeq2Seq.from_pretrained("Dev372/HarshDev-whisper-base-English_2000")Quick Links
English Whisper Model
This model is a fine-tuned version of openai/whisper-small.en on the Medical dataset. It achieves the following results on the evaluation set:
- Loss: 0.1242
- Wer: 8.5027
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: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0566 | 3.0030 | 1000 | 0.1344 | 9.0419 |
| 0.009 | 6.0060 | 2000 | 0.1242 | 8.5027 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 34
Model tree for Dev372/HarshDev-whisper-base-English_2000
Base model
openai/whisper-small.enDataset used to train Dev372/HarshDev-whisper-base-English_2000
Evaluation results
- Wer on Medicalself-reported8.503
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Dev372/HarshDev-whisper-base-English_2000")