update model card README.md
Browse files
README.md
CHANGED
|
@@ -1,6 +1,70 @@
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
-
-
|
| 4 |
-
|
| 5 |
-
-
|
| 6 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- wer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: whisper-small-ISSAI_KSC_335RS
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# whisper-small-ISSAI_KSC_335RS
|
| 15 |
+
|
| 16 |
+
This model was trained from scratch on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.1140
|
| 19 |
+
- Wer: 14.5474
|
| 20 |
+
- Cer: 3.3911
|
| 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: 16
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_steps: 100
|
| 46 |
+
- training_steps: 5001
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|
|
| 53 |
+
| 0.0918 | 0.11 | 500 | 0.1361 | 17.5287 | 4.1649 |
|
| 54 |
+
| 0.0795 | 0.22 | 1000 | 0.1327 | 16.8463 | 4.0455 |
|
| 55 |
+
| 0.0783 | 0.33 | 1500 | 0.1311 | 16.7385 | 3.9758 |
|
| 56 |
+
| 0.0699 | 0.43 | 2000 | 0.1273 | 16.5050 | 3.9360 |
|
| 57 |
+
| 0.0705 | 0.54 | 2500 | 0.1230 | 15.8944 | 3.8489 |
|
| 58 |
+
| 0.0622 | 0.65 | 3000 | 0.1194 | 16.2177 | 3.8514 |
|
| 59 |
+
| 0.0642 | 0.76 | 3500 | 0.1157 | 14.7989 | 3.5230 |
|
| 60 |
+
| 0.0697 | 0.87 | 4000 | 0.1152 | 15.1221 | 3.5802 |
|
| 61 |
+
| 0.0658 | 0.98 | 4500 | 0.1121 | 14.6731 | 3.4608 |
|
| 62 |
+
| 0.0271 | 1.09 | 5000 | 0.1140 | 14.5474 | 3.3911 |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
### Framework versions
|
| 66 |
+
|
| 67 |
+
- Transformers 4.27.0.dev0
|
| 68 |
+
- Pytorch 1.13.1+cu116
|
| 69 |
+
- Datasets 2.10.1
|
| 70 |
+
- Tokenizers 0.13.2
|