Downloads · 30 days
6
12% of all-time downloads
whisper-medium-train_noise3
adityarra07/whisper-medium-train_noise3
whisper-medium-train_noise3 is a automatic speech recognition model from adityarra07. 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
49
Public
Repo size
21.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin3.1 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Feb 20, 2024
- Updated
- Feb 21, 2024
- SHA
- 9219f600
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. -->
whisper-medium-train_noise3
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: 0.1641
- Wer: 7.3711
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2575 | 1.0 | 1385 | 0.1408 | 7.9993 |
| 0.0824 | 2.0 | 2770 | 0.1419 | 7.4266 |
| 0.0356 | 3.0 | 4155 | 0.1427 | 7.2788 |
| 0.0131 | 4.0 | 5540 | 0.1548 | 7.3157 |
| 0.0039 | 5.0 | 6925 | 0.1588 | 7.1864 |
| 0.0011 | 6.0 | 8310 | 0.1641 | 7.3711 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Feb 20, 2024
- Updated
- Feb 21, 2024