Commit
•
4002d6e
1
Parent(s):
47b3dd5
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- wer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: whisper-atcosim3
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# whisper-atcosim3
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.0476
|
| 20 |
+
- Wer: 0.0198
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 1e-05
|
| 40 |
+
- train_batch_size: 2
|
| 41 |
+
- eval_batch_size: 2
|
| 42 |
+
- seed: 42
|
| 43 |
+
- distributed_type: multi-GPU
|
| 44 |
+
- num_devices: 2
|
| 45 |
+
- gradient_accumulation_steps: 8
|
| 46 |
+
- total_train_batch_size: 32
|
| 47 |
+
- total_eval_batch_size: 4
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: linear
|
| 50 |
+
- lr_scheduler_warmup_steps: 150
|
| 51 |
+
- training_steps: 600
|
| 52 |
+
- mixed_precision_training: Native AMP
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 57 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 58 |
+
| 0.8218 | 0.2 | 50 | 0.3785 | 0.1451 |
|
| 59 |
+
| 0.1429 | 0.39 | 100 | 0.1213 | 0.0714 |
|
| 60 |
+
| 0.1155 | 0.59 | 150 | 0.0807 | 0.0517 |
|
| 61 |
+
| 0.0764 | 0.79 | 200 | 0.0652 | 0.0272 |
|
| 62 |
+
| 0.0724 | 0.98 | 250 | 0.0607 | 0.0393 |
|
| 63 |
+
| 0.0357 | 1.18 | 300 | 0.0569 | 0.0242 |
|
| 64 |
+
| 0.03 | 1.38 | 350 | 0.0553 | 0.0243 |
|
| 65 |
+
| 0.0325 | 1.57 | 400 | 0.0556 | 0.0228 |
|
| 66 |
+
| 0.03 | 1.77 | 450 | 0.0501 | 0.0242 |
|
| 67 |
+
| 0.0232 | 1.97 | 500 | 0.0485 | 0.0205 |
|
| 68 |
+
| 0.0143 | 2.16 | 550 | 0.0480 | 0.0194 |
|
| 69 |
+
| 0.0105 | 2.36 | 600 | 0.0476 | 0.0198 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- Transformers 4.29.0
|
| 75 |
+
- Pytorch 2.0.0+cu117
|
| 76 |
+
- Datasets 2.12.0
|
| 77 |
+
- Tokenizers 0.11.0
|