Downloads · 30 days
51
1% of all-time downloads
whisper-large-v3-japanese-4k-steps
drewschaub/whisper-large-v3-japanese-4k-steps
whisper-large-v3-japanese-4k-steps is a automatic speech recognition model from drewschaub. 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
8.2K
Public
Parameters
1.5B
6.2 GB on disk
Likes
7
Public
Repo makeup
Click a slice to open those files.
.safetensors6.2 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Feb 17, 2024
- Updated
- Feb 18, 2024
- SHA
- a86b0ca6
Base models
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-v3-japanese-4k-steps
This model is a fine-tuned version of openai/whisper-large-v3 on the Common Voice 16.1 dataset. I followed a post by Sanchit Gandhi, https://huggingface.co/blog/fine-tune-whisper It took 24 hours using an A100 on Google Colab to complete 4000 steps using the Common Voice 16.1 dataset. Training loss dropped over epochs but validation loss increased, so textbook overfitting. Furthermore, WER increased. It achieves the following results on the evaluation set:
- Loss: 0.4057
- Wer: 18.2149
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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- 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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1374 | 1.02 | 1000 | 0.3618 | 11.983182 |
| 0.0508 | 2.04 | 2000 | 0.3658 | 17.554657 |
| 0.0206 | 3.05 | 3000 | 0.3904 | 21.087484 |
| 0.0066 | 4.07 | 4000 | 0.4057 | 18.214909 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- ja
- Created
- Feb 17, 2024
- Updated
- Feb 18, 2024