Downloads · 30 days
8
20% of all-time downloads
finetune_v14
tz3/finetune_v14
finetune_v14 is a automatic speech recognition model from tz3. 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
41
Public
Parameters
1.6B
25.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6.4 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Jul 15, 2024
- Updated
- Jul 16, 2024
- SHA
- 24c7befd
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. -->
finetune_v14
This model is a fine-tuned version of openai/whisper-large-v3 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6836
- Wer: 39.4400
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: 16
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5
- training_steps: 80
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 7.2727 | 10 | 0.6533 | 30.4626 |
| No log | 14.5455 | 20 | 0.6367 | 29.8539 |
| No log | 21.8182 | 30 | 0.6772 | 29.5192 |
| No log | 29.0909 | 40 | 0.6792 | 34.9057 |
| 0.1995 | 36.3636 | 50 | 0.6777 | 180.6147 |
| 0.1995 | 43.6364 | 60 | 0.6782 | 33.9318 |
| 0.1995 | 50.9091 | 70 | 0.6821 | 37.4924 |
| 0.1995 | 58.1818 | 80 | 0.6836 | 39.4400 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.2.0
- Datasets 2.20.0
- Tokenizers 0.19.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Jul 15, 2024
- Updated
- Jul 16, 2024