Downloads · 30 days
6
13% of all-time downloads
whisper-tiny-til-asr
fishjojo1/whisper-tiny-til-asr
whisper-tiny-til-asr is a automatic speech recognition model from fishjojo1. 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
46
Public
Parameters
37.8M
755 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors151 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- May 20, 2024
- Updated
- May 20, 2024
- SHA
- c6449353
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-tiny-til-asr
This model is a fine-tuned version of openai/whisper-tiny.en on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0001
- Wer: 0.0166
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: 3.7500000000000003e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.002 | 1.0152 | 200 | 0.0040 | 0.1163 |
| 0.0001 | 2.0305 | 400 | 0.0003 | 0.0499 |
| 0.0001 | 3.0457 | 600 | 0.0003 | 0.0499 |
| 0.0 | 4.0609 | 800 | 0.0001 | 0.0166 |
| 0.0 | 5.0761 | 1000 | 0.0001 | 0.0166 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- May 20, 2024
- Updated
- May 20, 2024