Downloads · 30 days
5K
4% of all-time downloads
whisper-tiny.en
eai6/whisper-tiny.en
whisper-tiny.en is a automatic speech recognition model from eai6. 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
128K
Public
Parameters
37.8M
5.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin151 MB · 50%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Sep 3, 2023
- Updated
- Mar 29, 2024
- SHA
- 335be21d
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-tiny.en
This model is a fine-tuned version of openai/whisper-tiny.en on the Azure-dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.0680
- Wer: 44.3486
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: 250
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.2415 | 1.38 | 250 | 0.6131 | 26.6609 |
| 0.3582 | 2.76 | 500 | 0.0882 | 43.0544 |
| 0.2094 | 4.14 | 750 | 0.0723 | 43.6583 |
| 0.1788 | 5.52 | 1000 | 0.0680 | 44.3486 |
Framework versions
- Transformers 4.39.1
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- en
- Created
- Sep 3, 2023
- Updated
- Mar 29, 2024