Downloads · 30 days
11
5% of all-time downloads
speechx-base-kannada
kuladeep2112/speechx-base-kannada
speechx-base-kannada is a automatic speech recognition model from kuladeep2112. 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
239
Public
Parameters
72.6M
2.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors290 MB · 99%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Mar 5, 2024
- Updated
- Mar 5, 2024
- SHA
- 3d7ddb19
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. -->
speechx-base-kannada
This model is a fine-tuned version of openai/whisper-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1144
- Wer: 42.3786
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: 32
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 250
- training_steps: 10000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2594 | 0.1 | 1000 | 0.3520 | 65.6421 |
| 0.21 | 0.2 | 2000 | 0.3178 | 60.5516 |
| 0.1507 | 0.3 | 3000 | 0.3030 | 58.7877 |
| 0.1304 | 0.4 | 4000 | 0.1244 | 39.0290 |
| 0.1139 | 0.5 | 5000 | 0.1108 | 37.6041 |
| 0.1068 | 0.6 | 6000 | 0.1039 | 36.0586 |
| 0.1548 | 1.08 | 7000 | 0.1739 | 51.1577 |
| 0.1189 | 1.18 | 8000 | 0.1828 | 54.5993 |
| 0.1666 | 1.28 | 9000 | 0.1811 | 53.4042 |
| 0.1124 | 1.38 | 10000 | 0.1144 | 42.3786 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Mar 5, 2024
- Updated
- Mar 5, 2024