Downloads · 30 days
13
37% of all-time downloads
whisper-medium-ft-no_noise
adityarra07/whisper-medium-ft-no_noise
whisper-medium-ft-no_noise 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
35
Public
Repo size
18.3 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
- Dec 24, 2023
- Updated
- Dec 25, 2023
- SHA
- 2f3cfe2a
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-ft-no_noise
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: 0.1833
- Wer: 8.4650
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 |
|---|---|---|---|---|
| 0.2467 | 1.0 | 1385 | 0.1544 | 9.1986 |
| 0.0814 | 2.0 | 2770 | 0.1470 | 9.2175 |
| 0.0355 | 3.0 | 4155 | 0.1549 | 9.0670 |
| 0.0131 | 4.0 | 5540 | 0.1683 | 8.8224 |
| 0.0041 | 5.0 | 6925 | 0.1771 | 8.7848 |
| 0.0011 | 6.0 | 8310 | 0.1833 | 8.4650 |
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
- Dec 24, 2023
- Updated
- Dec 25, 2023