Downloads · 30 days
5
9% of all-time downloads
whisper-medium-4-F
nicolarsen/whisper-medium-4-F
whisper-medium-4-F is a automatic speech recognition model from nicolarsen. 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
54
Public
Parameters
764M
24.4 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
- Apr 20, 2024
- Updated
- Apr 20, 2024
- SHA
- 7c4b940c
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 da-nst
This model is a fine-tuned version of openai/whisper-medium on the common_voice_16_1 dataset. It achieves the following results on the evaluation set:
- Loss: 0.9322
- Wer: 29.1888
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- 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: 8000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0044 | 4.02 | 1000 | 0.9078 | 32.9698 |
| 0.0039 | 9.01 | 2000 | 0.8743 | 31.2338 |
| 0.0014 | 13.02 | 3000 | 0.8763 | 30.7476 |
| 0.0 | 18.01 | 4000 | 0.8731 | 30.0250 |
| 0.0 | 23.0 | 5000 | 0.8994 | 29.5024 |
| 0.0 | 27.02 | 6000 | 0.9165 | 29.3615 |
| 0.0 | 32.01 | 7000 | 0.9277 | 29.2297 |
| 0.0 | 36.03 | 8000 | 0.9322 | 29.1888 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Apr 20, 2024
- Updated
- Apr 20, 2024