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/Finetuned_whisper_small")
model = AutoModelForSpeechSeq2Seq.from_pretrained("Dev372/Finetuned_whisper_small")Quick Links
Finetuned_whisper_small
This model is a fine-tuned version of openai/whisper-small on the Dev372/Cardiology_Medical_STT_Dataset_split dataset. It achieves the following results on the evaluation set:
- Loss: 0.0174
- Wer: 1.0940
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: 15
- 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: 1500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0008 | 6.0976 | 500 | 0.0154 | 1.2561 |
| 0.0001 | 12.1951 | 1000 | 0.0169 | 1.0940 |
| 0.0001 | 18.2927 | 1500 | 0.0174 | 1.0940 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 5
Model tree for Dev372/Finetuned_whisper_small
Base model
openai/whisper-smallEvaluation results
- Wer on Dev372/Cardiology_Medical_STT_Dataset_splitself-reported1.094
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Dev372/Finetuned_whisper_small")