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: 0.1002
- Precision: 0.0339
- Recall: 0.0359
- F1: 0.0348
- Precision Median: 0.0
- Recall Median: 0.0
- F1 Median: 0.0
- Precision Max: 0.9231
- Recall Max: 1.0
- F1 Max: 0.9600
- Precision Min: 0.0
- Recall Min: 0.0
- F1 Min: 0.0
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: 8
- 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: 200
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Precision Median | Recall Median | F1 Median | Precision Max | Recall Max | F1 Max | Precision Min | Recall Min | F1 Min |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.2011 | 0.2 | 500 | 0.2334 | 0.0486 | 0.0506 | 0.0495 | 0.0 | 0.0 | 0.0 | 0.8947 | 0.9444 | 0.9189 | 0.0 | 0.0 | 0.0 |
| 0.0923 | 0.4 | 1000 | 0.1190 | 0.0946 | 0.1001 | 0.0972 | 0.0 | 0.0 | 0.0 | 0.9524 | 1.0 | 0.9756 | 0.0 | 0.0 | 0.0 |
| 0.033 | 0.59 | 1500 | 0.1151 | 0.0468 | 0.0491 | 0.0479 | 0.0 | 0.0 | 0.0 | 0.9375 | 1.0 | 0.9600 | 0.0 | 0.0 | 0.0 |
| 0.0323 | 0.79 | 2000 | 0.1002 | 0.0339 | 0.0359 | 0.0348 | 0.0 | 0.0 | 0.0 | 0.9231 | 1.0 | 0.9600 | 0.0 | 0.0 | 0.0 |
Framework versions
- Transformers 4.36.2
- Pytorch 1.13.1+cu117
- Datasets 2.16.1
- Tokenizers 0.15.0