Downloads · 30 days
4
10% of all-time downloads
whisper-small-ko-E10_Y_freq_speed
Gummybear05/whisper-small-ko-E10_Y_freq_speed
whisper-small-ko-E10_Y_freq_speed is a automatic speech recognition model from Gummybear05. 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
39
Public
Parameters
242M
14.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors967 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Dec 22, 2023
- Updated
- Dec 22, 2023
- SHA
- 4878c5ba
Base models
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-small-ko-E10_Y_freq_speed
This model is a fine-tuned version of openai/whisper-small on the aihub Y dialogue dataset. It achieves the following results on the evaluation set:
- Loss: 0.2340
- Cer: 7.8242
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
- 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: 50
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.4741 | 0.13 | 100 | 0.3013 | 7.2133 |
| 0.2844 | 0.26 | 200 | 0.2553 | 7.1370 |
| 0.2397 | 0.39 | 300 | 0.2656 | 7.7538 |
| 0.2107 | 0.52 | 400 | 0.2466 | 7.0900 |
| 0.2067 | 0.64 | 500 | 0.2472 | 6.9314 |
| 0.1802 | 0.77 | 600 | 0.2432 | 6.7375 |
| 0.185 | 0.9 | 700 | 0.2399 | 7.0665 |
| 0.0796 | 1.03 | 800 | 0.2364 | 7.0547 |
| 0.0664 | 1.16 | 900 | 0.2349 | 6.7963 |
| 0.0736 | 1.29 | 1000 | 0.2360 | 7.6480 |
| 0.0729 | 1.42 | 1100 | 0.2365 | 7.1487 |
| 0.072 | 1.55 | 1200 | 0.2334 | 7.3191 |
| 0.0694 | 1.68 | 1300 | 0.2334 | 7.6539 |
| 0.067 | 1.81 | 1400 | 0.2342 | 7.7068 |
| 0.0719 | 1.93 | 1500 | 0.2340 | 7.8242 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.0
- Tokenizers 0.15.0
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- hi
- Created
- Dec 22, 2023
- Updated
- Dec 22, 2023