Downloads · 30 days
4
11% of all-time downloads
whisper-medium-ro_common_voice
AdaCodruta/whisper-medium-ro_common_voice
whisper-medium-ro_common_voice is a automatic speech recognition model from AdaCodruta. 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
36
Public
Parameters
764M
6.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.1 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Dec 9, 2024
- Updated
- Dec 9, 2024
- SHA
- ca64bffc
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. -->
whisper-medium-ro_private_dataset
This model is a fine-tuned version of openai/whisper-medium on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2179
- Wer Ortho: 14.3915
- Wer: 12.8568
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: 32
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.0039 | 6.2112 | 500 | 0.2024 | 14.7619 | 13.1275 |
| 0.0005 | 12.4224 | 1000 | 0.2179 | 14.3915 | 12.8568 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1+cu118
- Datasets 3.1.0
- Tokenizers 0.20.3
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Dec 9, 2024
- Updated
- Dec 9, 2024