Downloads · 30 days
3
17% of all-time downloads
whisper-small-E30_freq_pause
Gummybear05/whisper-small-E30_freq_pause
whisper-small-E30_freq_pause 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
18
Public
Parameters
242M
15.5 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
- Oct 14, 2024
- Updated
- Oct 14, 2024
- SHA
- 8122eda6
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-Yfreq_speed_pause
This model is a fine-tuned version of openai/whisper-small on the aihub old30 adult freq pause changed dataset. It achieves the following results on the evaluation set:
- Loss: 0.1841
- Cer: 4.9930
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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- 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 |
|---|---|---|---|---|
| 0.2772 | 0.1289 | 100 | 0.2544 | 6.4145 |
| 0.166 | 0.2579 | 200 | 0.2291 | 6.5143 |
| 0.1593 | 0.3868 | 300 | 0.2266 | 6.0855 |
| 0.1453 | 0.5158 | 400 | 0.2137 | 6.1090 |
| 0.1141 | 0.6447 | 500 | 0.2080 | 5.7507 |
| 0.1142 | 0.7737 | 600 | 0.1980 | 5.2984 |
| 0.1159 | 0.9026 | 700 | 0.1985 | 5.6391 |
| 0.0568 | 1.0316 | 800 | 0.1871 | 4.8990 |
| 0.0471 | 1.1605 | 900 | 0.1883 | 5.0047 |
| 0.0434 | 1.2895 | 1000 | 0.1893 | 4.9636 |
| 0.0408 | 1.4184 | 1100 | 0.1883 | 5.0164 |
| 0.0383 | 1.5474 | 1200 | 0.1861 | 5.0341 |
| 0.0402 | 1.6763 | 1300 | 0.1865 | 5.0987 |
| 0.0367 | 1.8053 | 1400 | 0.1854 | 4.9636 |
| 0.0386 | 1.9342 | 1500 | 0.1841 | 4.9930 |
Framework versions
- Transformers 4.46.0.dev0
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- hi
- Created
- Oct 14, 2024
- Updated
- Oct 14, 2024