Downloads · 30 days
11
3% of all-time downloads
whisper-large-v2-he-1
Shiry/whisper-large-v2-he-1
whisper-large-v2-he-1 is a automatic speech recognition model from Shiry. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
341
Public
Repo size
30.9 GB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.bin6.2 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Dec 20, 2022
- Updated
- Dec 22, 2022
- SHA
- 1bf1bf15
Datasets
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
Whisper Large V2 Hebrew
This model is a fine-tuned version of openai/whisper-large-v2 on the google/fleurs he_il dataset. It achieves the following results on the evaluation set:
- Loss: 0.4106
- Wer: 27.2504
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-06
- train_batch_size: 128
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 512
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- training_steps: 200
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.425 | 24.01 | 50 | 0.4106 | 27.2504 |
| 0.1906 | 49.01 | 100 | 0.4420 | 29.0131 |
| 0.0982 | 74.01 | 150 | 0.4795 | 30.3063 |
| 0.0717 | 99.01 | 200 | 0.4945 | 30.8915 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- he
- Created
- Dec 20, 2022
- Updated
- Dec 22, 2022