update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- wer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: whisper-tiny-v2-ta_tf32_adamBetas_2
|
| 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-tiny-v2-ta_tf32_adamBetas_2
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.3491
|
| 20 |
+
- Wer: 43.1477
|
| 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: 1.5e-05
|
| 40 |
+
- train_batch_size: 4
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 8
|
| 44 |
+
- total_train_batch_size: 32
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_steps: 500
|
| 48 |
+
- training_steps: 4000
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
| 54 |
+
| 0.6508 | 0.11 | 300 | 0.5656 | 54.3341 |
|
| 55 |
+
| 0.4612 | 0.21 | 600 | 0.4615 | 50.4600 |
|
| 56 |
+
| 0.408 | 0.32 | 900 | 0.4190 | 47.4576 |
|
| 57 |
+
| 0.3692 | 0.42 | 1200 | 0.4001 | 52.0581 |
|
| 58 |
+
| 0.3486 | 0.53 | 1500 | 0.3858 | 51.2349 |
|
| 59 |
+
| 0.3245 | 0.63 | 1800 | 0.3791 | 45.6174 |
|
| 60 |
+
| 0.3274 | 0.74 | 2100 | 0.3632 | 42.1792 |
|
| 61 |
+
| 0.2985 | 0.84 | 2400 | 0.3566 | 43.7288 |
|
| 62 |
+
| 0.2849 | 0.95 | 2700 | 0.3548 | 43.3898 |
|
| 63 |
+
| 0.2717 | 1.05 | 3000 | 0.3491 | 43.1477 |
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
### Framework versions
|
| 67 |
+
|
| 68 |
+
- Transformers 4.28.0.dev0
|
| 69 |
+
- Pytorch 1.12.1
|
| 70 |
+
- Datasets 2.11.0
|
| 71 |
+
- Tokenizers 0.13.3
|