Downloads · 30 days
3
14% of all-time downloads
whisper-tiny-2023-01-30
Mehtap/whisper-tiny-2023-01-30
whisper-tiny-2023-01-30 is a automatic speech recognition model from Mehtap. 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
21
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
- Jan 30, 2023
- Updated
- Jan 30, 2023
- SHA
- b5ad4c60
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. -->
tiny Turkish Whisper (tTW)
This model is a fine-tuned version of openai/whisper-tiny on the Ermetal Meetings dataset. It achieves the following results on the evaluation set:
- Loss: 6.0735
- Wer: 1.4939
- Cer: 1.0558
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: 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: 500
- training_steps: 1
Training results
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.12.1+cu102
- Datasets 2.5.2
- Tokenizers 0.13.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- tr
- Created
- Jan 30, 2023
- Updated
- Jan 30, 2023