Commit
•
35c0f68
1
Parent(s):
92a42c5
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- wer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: whisper-small-mn-11
|
| 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-small-mn-11
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.0138
|
| 20 |
+
- Wer: 51.9664
|
| 21 |
+
- Cer: 19.8770
|
| 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: 1e-05
|
| 41 |
+
- train_batch_size: 32
|
| 42 |
+
- eval_batch_size: 32
|
| 43 |
+
- seed: 42
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- lr_scheduler_warmup_steps: 500
|
| 47 |
+
- training_steps: 15000
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 53 |
+
|:-------------:|:------:|:-----:|:---------------:|:-------:|:-------:|
|
| 54 |
+
| 0.0025 | 32.26 | 1000 | 0.8913 | 53.6214 | 20.6866 |
|
| 55 |
+
| 0.0007 | 64.52 | 2000 | 0.9326 | 52.1685 | 19.5991 |
|
| 56 |
+
| 0.0001 | 96.77 | 3000 | 1.0138 | 51.9664 | 19.8770 |
|
| 57 |
+
| 0.0001 | 129.03 | 4000 | 1.0639 | 52.1248 | 19.9178 |
|
| 58 |
+
| 0.0 | 161.29 | 5000 | 1.1236 | 52.0428 | 19.9652 |
|
| 59 |
+
| 0.0 | 193.55 | 6000 | 1.1677 | 52.4634 | 20.0351 |
|
| 60 |
+
| 0.0 | 225.81 | 7000 | 1.2224 | 52.5836 | 20.1258 |
|
| 61 |
+
| 0.0 | 258.06 | 8000 | 1.2633 | 52.7310 | 20.2073 |
|
| 62 |
+
| 0.0 | 290.32 | 9000 | 1.3152 | 52.8184 | 20.2273 |
|
| 63 |
+
| 0.0 | 322.58 | 10000 | 1.3530 | 52.9495 | 20.3080 |
|
| 64 |
+
| 0.0 | 354.84 | 11000 | 1.3995 | 53.0260 | 20.3088 |
|
| 65 |
+
| 0.0 | 387.1 | 12000 | 1.4306 | 52.9878 | 20.2057 |
|
| 66 |
+
| 0.0 | 419.35 | 13000 | 1.4674 | 52.9714 | 20.3113 |
|
| 67 |
+
| 0.0 | 451.61 | 14000 | 1.4859 | 52.9386 | 20.2947 |
|
| 68 |
+
| 0.0 | 483.87 | 15000 | 1.4994 | 52.9768 | 20.3280 |
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
### Framework versions
|
| 72 |
+
|
| 73 |
+
- Transformers 4.26.0.dev0
|
| 74 |
+
- Pytorch 1.13.0+cu117
|
| 75 |
+
- Datasets 2.7.1.dev0
|
| 76 |
+
- Tokenizers 0.13.2
|