Downloads · 30 days
5
15% of all-time downloads
nr-whisper-tiny
dadajuan123/nr-whisper-tiny
nr-whisper-tiny is a automatic speech recognition model from dadajuan123. 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
33
Public
Parameters
37.8M
302 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors151 MB · 99%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Jan 31, 2024
- Updated
- Jan 31, 2024
- SHA
- 50852728
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. -->
nr-whisper-tiny
This model is a fine-tuned version of openai/whisper-tiny on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.0791
- Wer: 400.0
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: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1814 | 100.0 | 100 | 1.2428 | 200.0 |
| 0.0001 | 200.0 | 200 | 1.0974 | 200.0 |
| 0.0 | 300.0 | 300 | 1.0920 | 300.0 |
| 0.0 | 400.0 | 400 | 1.0876 | 400.0 |
| 0.0 | 500.0 | 500 | 1.0842 | 400.0 |
| 0.0 | 600.0 | 600 | 1.0816 | 400.0 |
| 0.0 | 700.0 | 700 | 1.0803 | 400.0 |
| 0.0 | 800.0 | 800 | 1.0799 | 400.0 |
| 0.0 | 900.0 | 900 | 1.0793 | 400.0 |
| 0.0 | 1000.0 | 1000 | 1.0791 | 400.0 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.2
- Datasets 2.16.1
- Tokenizers 0.15.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Jan 31, 2024
- Updated
- Jan 31, 2024