Downloads · 30 days
5
9% of all-time downloads
whisper-small-ko-E30_Y_freq_speed
Gummybear05/whisper-small-ko-E30_Y_freq_speed
whisper-small-ko-E30_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
57
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 23, 2023
- Updated
- Dec 23, 2023
- SHA
- 431ee4c2
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-E30_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: 0.1876
- Cer: 5.2573
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 |
|---|---|---|---|---|
| 0.4514 | 0.13 | 100 | 0.2782 | 6.3910 |
| 0.2636 | 0.26 | 200 | 0.2298 | 6.1913 |
| 0.2355 | 0.39 | 300 | 0.2313 | 6.5789 |
| 0.2075 | 0.52 | 400 | 0.2121 | 6.1149 |
| 0.1899 | 0.64 | 500 | 0.2107 | 5.9622 |
| 0.1746 | 0.77 | 600 | 0.2040 | 5.8212 |
| 0.1791 | 0.9 | 700 | 0.1974 | 5.6685 |
| 0.0826 | 1.03 | 800 | 0.1924 | 5.4335 |
| 0.0725 | 1.16 | 900 | 0.1959 | 5.4570 |
| 0.072 | 1.29 | 1000 | 0.1942 | 5.2749 |
| 0.0658 | 1.42 | 1100 | 0.1935 | 5.4746 |
| 0.0639 | 1.55 | 1200 | 0.1894 | 5.2867 |
| 0.0658 | 1.68 | 1300 | 0.1891 | 5.3043 |
| 0.0606 | 1.81 | 1400 | 0.1876 | 5.1985 |
| 0.0648 | 1.93 | 1500 | 0.1876 | 5.2573 |
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 23, 2023
- Updated
- Dec 23, 2023