Downloads · 30 days
9
31% of all-time downloads
atcosim_fn_tiny
Jakaria/atcosim_fn_tiny
atcosim_fn_tiny is a automatic speech recognition model from Jakaria. 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
29
Public
Repo size
302 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin151 MB · 99%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Dec 23, 2022
- Updated
- Dec 23, 2022
- SHA
- cd489023
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. -->
atcosim_corpus
This model is a fine-tuned version of openai/whisper-tiny on the atcosim_corpus dataset. It achieves the following results on the evaluation set:
- Loss: 0.0623
- Wer: 2.4909
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- 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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0281 | 2.1 | 1000 | 0.0716 | 4.1957 |
| 0.0051 | 4.19 | 2000 | 0.0650 | 2.7162 |
| 0.0009 | 6.29 | 3000 | 0.0624 | 2.4733 |
| 0.0005 | 8.39 | 4000 | 0.0623 | 2.4909 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.6.1
- Tokenizers 0.13.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- en
- Created
- Dec 23, 2022
- Updated
- Dec 23, 2022