Downloads · 30 days
8
14% of all-time downloads
gyeongsan_1_6_model_1000
Marcusxx/gyeongsan_1_6_model_1000
gyeongsan_1_6_model_1000 is a automatic speech recognition model from Marcusxx. 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
764M
30.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.1 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Jul 18, 2024
- Updated
- Jul 21, 2024
- SHA
- 0873aace
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. -->
gyeongsan_1_6_model_1000
This model is a fine-tuned version of openai/whisper-medium on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1637
- Cer: 11.3512
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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 10000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.2291 | 0.0450 | 2000 | 0.2172 | 12.9641 |
| 0.2096 | 0.0901 | 4000 | 0.1984 | 12.5073 |
| 0.1797 | 0.1351 | 6000 | 0.1823 | 12.1606 |
| 0.1472 | 0.1801 | 8000 | 0.1702 | 11.5960 |
| 0.152 | 0.2252 | 10000 | 0.1637 | 11.3512 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.2.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Jul 18, 2024
- Updated
- Jul 21, 2024