update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- wer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: whisper-base-ar-quran
|
| 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-base-ar-quran
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.0839
|
| 20 |
+
- Wer: 5.7544
|
| 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: 0.0001
|
| 40 |
+
- train_batch_size: 16
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 43 |
+
- distributed_type: multi-GPU
|
| 44 |
+
- num_devices: 8
|
| 45 |
+
- total_train_batch_size: 128
|
| 46 |
+
- total_eval_batch_size: 64
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- lr_scheduler_warmup_steps: 500
|
| 50 |
+
- training_steps: 5000
|
| 51 |
+
- mixed_precision_training: Native AMP
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 56 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
| 57 |
+
| 0.1092 | 0.05 | 250 | 0.1969 | 13.3890 |
|
| 58 |
+
| 0.0361 | 0.1 | 500 | 0.1583 | 10.6375 |
|
| 59 |
+
| 0.0192 | 0.15 | 750 | 0.1109 | 8.8468 |
|
| 60 |
+
| 0.0144 | 0.2 | 1000 | 0.1157 | 7.9754 |
|
| 61 |
+
| 0.008 | 0.25 | 1250 | 0.1000 | 7.5360 |
|
| 62 |
+
| 0.0048 | 1.03 | 1500 | 0.0933 | 6.8227 |
|
| 63 |
+
| 0.0113 | 1.08 | 1750 | 0.0955 | 6.9638 |
|
| 64 |
+
| 0.0209 | 1.13 | 2000 | 0.0824 | 6.3586 |
|
| 65 |
+
| 0.0043 | 1.18 | 2250 | 0.0830 | 6.3444 |
|
| 66 |
+
| 0.002 | 1.23 | 2500 | 0.1015 | 6.3025 |
|
| 67 |
+
| 0.0013 | 2.01 | 2750 | 0.0863 | 6.0639 |
|
| 68 |
+
| 0.0014 | 2.06 | 3000 | 0.0905 | 6.0213 |
|
| 69 |
+
| 0.0018 | 2.11 | 3250 | 0.0864 | 6.0293 |
|
| 70 |
+
| 0.0008 | 2.16 | 3500 | 0.0887 | 5.9308 |
|
| 71 |
+
| 0.0029 | 2.21 | 3750 | 0.0777 | 5.9159 |
|
| 72 |
+
| 0.0022 | 2.26 | 4000 | 0.0847 | 5.8749 |
|
| 73 |
+
| 0.0005 | 3.05 | 4250 | 0.0827 | 5.8352 |
|
| 74 |
+
| 0.0003 | 3.1 | 4500 | 0.0826 | 5.7800 |
|
| 75 |
+
| 0.0006 | 3.15 | 4750 | 0.0833 | 5.7625 |
|
| 76 |
+
| 0.0003 | 3.2 | 5000 | 0.0839 | 5.7544 |
|
| 77 |
+
|
| 78 |
+
|
| 79 |
+
### Framework versions
|
| 80 |
+
|
| 81 |
+
- Transformers 4.26.0.dev0
|
| 82 |
+
- Pytorch 1.13.0+cu117
|
| 83 |
+
- Datasets 2.7.1.dev0
|
| 84 |
+
- Tokenizers 0.13.2
|