Downloads · 30 days
6
27% of all-time downloads
fs-w-he-base
hiwden00/fs-w-he-base
fs-w-he-base is a automatic speech recognition model from hiwden00. 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
22
Public
Parameters
72.6M
2.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors290 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Oct 2, 2024
- Updated
- Oct 2, 2024
- SHA
- 29a63163
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. -->
fs-w-he-base
This model is a fine-tuned version of openai/whisper-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1453
- Wer: 110.8262
- Cer: 93.0350
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: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 7.2383 | 4.5872 | 500 | 7.6104 | 178.9174 | 140.9825 |
| 1.348 | 9.1743 | 1000 | 2.0785 | 113.0579 | 96.7795 |
| 0.4859 | 13.7615 | 1500 | 1.1437 | 132.2412 | 113.7066 |
| 0.2809 | 18.3486 | 2000 | 0.9320 | 156.9801 | 142.7087 |
| 0.1568 | 22.9358 | 2500 | 0.9841 | 124.2640 | 115.1666 |
| 0.041 | 27.5229 | 3000 | 1.0475 | 130.6743 | 110.1941 |
| 0.0091 | 32.1101 | 3500 | 1.0947 | 124.5014 | 103.2205 |
| 0.0016 | 36.6972 | 4000 | 1.1475 | 137.9392 | 119.5981 |
| 0.0001 | 41.2844 | 4500 | 1.1431 | 124.0741 | 103.3494 |
| 0.0001 | 45.8716 | 5000 | 1.1453 | 110.8262 | 93.0350 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Oct 2, 2024
- Updated
- Oct 2, 2024