Downloads · 30 days
11
17% of all-time downloads
whisper-small-hi
spsither/whisper-small-hi
whisper-small-hi is a automatic speech recognition model from spsither. 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
63
Public
Repo size
29.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin6.2 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Aug 16, 2023
- Updated
- Aug 31, 2023
- SHA
- e1f34a3c
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-small-hi
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3488
- Wer: 18.8573
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: 500
- training_steps: 4000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1899 | 3.02 | 1000 | 0.3311 | 22.3674 |
| 0.0179 | 6.04 | 2000 | 0.3252 | 19.8309 |
| 0.0026 | 9.06 | 3000 | 0.3382 | 18.8189 |
| 0.0009 | 12.08 | 4000 | 0.3488 | 18.8573 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Aug 16, 2023
- Updated
- Aug 31, 2023