Downloads · 30 days
3
13% of all-time downloads
real-data-synth-data-1600-1-Standard-B-v0-whisper-small
IoanaLiviaPopescu/real-data-synth-data-1600-1-Standard-B-v0-whisper-small
real-data-synth-data-1600-1-Standard-B-v0-whisper-small is a automatic speech recognition model from IoanaLiviaPopescu. 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
23
Public
Parameters
242M
4.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors967 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Jun 16, 2025
- Updated
- Jun 16, 2025
- SHA
- 5e9898ed
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. -->
IoanaLiviaPopescu/IoanaLiviaPopescu/real-data-synth-data-1600-1-Standard-B-v0-whisper-small
This model is a fine-tuned version of openai/whisper-small on the IoanaLiviaPopescu/RealVoiceSynthVoice-1600-1-Standard-B-v0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3743
- Wer: 16.8173
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
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 0 | 0 | 0.6024 | 27.8812 |
| 0.2466 | 1.0 | 63 | 0.3919 | 17.2414 |
| 0.0899 | 2.0 | 126 | 0.3716 | 16.8357 |
| 0.0465 | 3.0 | 189 | 0.3743 | 16.8173 |
| 0.0265 | 4.0 | 252 | 0.3880 | 17.2414 |
| 0.0187 | 5.0 | 315 | 0.4032 | 17.4073 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- ro
- Created
- Jun 16, 2025
- Updated
- Jun 16, 2025