Downloads · 30 days
9
24% of all-time downloads
whisper-small-hi22
Marwan-Kasem/whisper-small-hi22
whisper-small-hi22 is a automatic speech recognition model from Marwan-Kasem. Use it when you need speech turned into text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
37
Public
Parameters
242M
14.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6.8 GB · 44%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- Model type
- whisper
- Access
- Public
- Created
- Mar 27, 2025
- Updated
- Apr 21, 2025
- SHA
- 950c4bd7
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-small-hi22
This model is a fine-tuned version of Marwan-Kasem/whisper-small-hi2 on the ami-ihm dataset. It achieves the following results on the evaluation set:
- eval_loss: 4.2314
- eval_wer: 1884.8103
- eval_runtime: 22628.8735
- eval_samples_per_second: 0.279
- eval_steps_per_second: 0.035
- epoch: 0.0922
- step: 2500
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: 3e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- 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: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.3.1
- Tokenizers 0.21.0
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- Created
- Mar 27, 2025
- Updated
- Apr 21, 2025