Downloads · 30 days
6
8% of all-time downloads
ft-whisperl-ja
HuyHoang1977/ft-whisperl-ja
ft-whisperl-ja is a automatic speech recognition model from HuyHoang1977. 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
78
Public
Parameters
1.5B
30.9 GB on disk
Likes
0
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
- Sep 26, 2025
- Updated
- Sep 26, 2025
- SHA
- 2ad1be20
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. -->
ft-whisperl-ja
This model is a fine-tuned version of openai/whisper-large-v3 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4399
- Wer: 71.8333
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: 2e-05
- train_batch_size: 6
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 24
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 200
- training_steps: 2500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2888 | 0.7361 | 500 | 0.4336 | 75.5 |
| 0.1475 | 1.4711 | 1000 | 0.4332 | 75.6667 |
| 0.0567 | 2.2061 | 1500 | 0.4210 | 73.1667 |
| 0.0433 | 2.9422 | 2000 | 0.4117 | 71.6667 |
| 0.0137 | 3.6772 | 2500 | 0.4399 | 71.8333 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.0
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Sep 26, 2025
- Updated
- Sep 26, 2025