Finetune Whisper on Frisian and English
Collection
Assessing Knowledge-Distillation Based Compression of Whisper Model for Frisian ASR
•
12 items
•
Updated
Whisper-Small En-10h
This model is a fine-tuned version of openai/whisper-small on the librispeech dataset. It achieves the following results on the evaluation set:
- Loss: 0.1307
- Wer: 3.9809
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: 5e-07
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 300
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.525 | 0.5556 | 100 | 0.7431 | 3.4571 |
| 0.382 | 1.1111 | 200 | 0.5645 | 3.4836 |
| 0.1704 | 1.6667 | 300 | 0.2111 | 4.0237 |
| 0.0953 | 2.2222 | 400 | 0.1527 | 4.1114 |
| 0.0904 | 2.7778 | 500 | 0.1404 | 4.0400 |
| 0.0784 | 3.3333 | 600 | 0.1355 | 4.0482 |
| 0.0793 | 3.8889 | 700 | 0.1331 | 3.9768 |
| 0.0776 | 4.4444 | 800 | 0.1318 | 3.9646 |
| 0.0629 | 5.0 | 900 | 0.1310 | 3.9830 |
| 0.0746 | 5.5556 | 1000 | 0.1307 | 3.9809 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 0
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for Pageee/FT-English-10ha
Base model
openai/whisper-small