Downloads · 30 days
4
24% of all-time downloads
whisper-large-v2-ft-my_dataset_letter_BV_no_split-241025-v1
dylanewbie/whisper-large-v2-ft-my_dataset_letter_BV_no_split-241025-v1
whisper-large-v2-ft-my_dataset_letter_BV_no_split-241025-v1 is a machine learning model from dylanewbie. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
17
Public
Repo size
7.9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors7.9 MB · 100%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Oct 25, 2024
- Updated
- Oct 25, 2024
- SHA
- fbff3ff6
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. -->
whisper-large-v2-ft-my_dataset_letter_BV_no_split-241025-v1
This model is a fine-tuned version of openai/whisper-large-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 7.5499
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 13.9778 | 1.0 | 2 | 13.5082 |
| 13.1164 | 2.0 | 4 | 11.4291 |
| 10.7363 | 3.0 | 6 | 9.4007 |
| 9.1462 | 4.0 | 8 | 8.5659 |
| 8.4123 | 5.0 | 10 | 8.1629 |
| 8.1021 | 6.0 | 12 | 7.9240 |
| 7.8847 | 7.0 | 14 | 7.7648 |
| 7.7321 | 8.0 | 16 | 7.6497 |
| 7.6318 | 9.0 | 18 | 7.5812 |
| 7.5679 | 10.0 | 20 | 7.5499 |
Framework versions
- PEFT 0.13.0
- Transformers 4.45.0.dev0
- Pytorch 2.3.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1
- Library
- peft
- License
- apache-2.0
- Created
- Oct 25, 2024
- Updated
- Oct 25, 2024