metadata
language:
- he
license: apache-2.0
base_model: openai/whisper-medium
tags:
- hf-asr-leaderboard
- generated_from_trainer
metrics:
- precision
- recall
- f1
model-index:
- name: he
results: []
he
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: 0.0582
- Precision: 0.0005
- Recall: 0.0005
- F1: 0.0005
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: 4e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
|---|---|---|---|---|---|---|
| 0.074 | 0.2 | 500 | 0.1027 | 0.0 | 0.0 | 0.0 |
| 0.0393 | 0.4 | 1000 | 0.0712 | 0.0 | 0.0 | 0.0 |
| 0.0161 | 0.59 | 1500 | 0.0597 | 0.0009 | 0.0009 | 0.0009 |
| 0.0114 | 0.79 | 2000 | 0.0582 | 0.0005 | 0.0005 | 0.0005 |
Framework versions
- Transformers 4.36.2
- Pytorch 1.13.1+cu117
- Datasets 2.16.1
- Tokenizers 0.15.0