metadata
library_name: transformers.js
license: apache-2.0
base_model:
- Hemg/audiotranscribe
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-medium-medical
results: []
pipeline_tag: automatic-speech-recognition
audiotranscribe (ONNX)
This is an ONNX version of Hemg/audiotranscribe. It was automatically converted and uploaded using this Hugging Face Space.
Usage with Transformers.js
See the pipeline documentation for automatic-speech-recognition: https://huggingface.co/docs/transformers.js/api/pipelines#module_pipelines.AutomaticSpeechRecognitionPipeline
whisper-medium-medical
This model is a fine-tuned version of openai/whisper-medium on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0562
- Wer: 10.7169
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: 32
- 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: 50
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.5008 | 0.5405 | 100 | 0.1965 | 12.0203 |
| 0.1034 | 1.0811 | 200 | 0.0870 | 12.2616 |
| 0.0563 | 1.6216 | 300 | 0.0642 | 8.3514 |
| 0.0238 | 2.1622 | 400 | 0.0610 | 11.6341 |
| 0.0129 | 2.7027 | 500 | 0.0562 | 10.7169 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0+cu118
- Datasets 3.3.1
- Tokenizers 0.21.0