Downloads · 30 days
4
15% of all-time downloads
whisper-medium-trial2
racheltlw/whisper-medium-trial2
whisper-medium-trial2 is a automatic speech recognition model from racheltlw. 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
27
Public
Repo size
9.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin3.1 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Apr 15, 2023
- Updated
- Apr 15, 2023
- SHA
- d3af282c
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-trial2
This model is a fine-tuned version of openai/whisper-medium on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4597
- Wer: 18.1818
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: 6.25e-06
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 128
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 200
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 2.2936 | 0.25 | 50 | 1.8141 | 19.8347 |
| 0.5292 | 0.5 | 100 | 0.6131 | 24.7934 |
| 0.204 | 0.75 | 150 | 0.5158 | 19.0083 |
| 0.1319 | 1.0 | 200 | 0.4597 | 18.1818 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1+cu116
- Datasets 2.11.0
- Tokenizers 0.13.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Apr 15, 2023
- Updated
- Apr 15, 2023