End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
language:
|
| 4 |
+
- ja
|
| 5 |
+
license: apache-2.0
|
| 6 |
+
base_model: openai/whisper-large-v3
|
| 7 |
+
tags:
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: Whisper Large v3
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# Whisper Large v3
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.0346
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 0.001
|
| 41 |
+
- train_batch_size: 8
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- lr_scheduler_warmup_steps: 50
|
| 47 |
+
- num_epochs: 3
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 54 |
+
| 0.0923 | 0.2151 | 20 | 0.0633 |
|
| 55 |
+
| 0.045 | 0.4301 | 40 | 0.0610 |
|
| 56 |
+
| 0.0664 | 0.6452 | 60 | 0.0720 |
|
| 57 |
+
| 0.0622 | 0.8602 | 80 | 0.0552 |
|
| 58 |
+
| 0.0589 | 1.0753 | 100 | 0.0781 |
|
| 59 |
+
| 0.0382 | 1.2903 | 120 | 0.0480 |
|
| 60 |
+
| 0.03 | 1.5054 | 140 | 0.0445 |
|
| 61 |
+
| 0.022 | 1.7204 | 160 | 0.0404 |
|
| 62 |
+
| 0.0201 | 1.9355 | 180 | 0.0387 |
|
| 63 |
+
| 0.0131 | 2.1505 | 200 | 0.0412 |
|
| 64 |
+
| 0.0111 | 2.3656 | 220 | 0.0366 |
|
| 65 |
+
| 0.0111 | 2.5806 | 240 | 0.0357 |
|
| 66 |
+
| 0.0142 | 2.7957 | 260 | 0.0346 |
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
### Framework versions
|
| 70 |
+
|
| 71 |
+
- PEFT 0.15.1
|
| 72 |
+
- Transformers 4.51.1
|
| 73 |
+
- Pytorch 2.6.0+cu124
|
| 74 |
+
- Datasets 3.5.0
|
| 75 |
+
- Tokenizers 0.21.1
|