Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: cc-by-nc-4.0
|
| 4 |
+
base_model: facebook/mms-1b-all
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- wer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: mms-1b-all-bem-natbed-n-model
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# mms-1b-all-bem-natbed-n-model
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.5579
|
| 22 |
+
- Wer: 0.4550
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 0.0003
|
| 42 |
+
- train_batch_size: 8
|
| 43 |
+
- eval_batch_size: 8
|
| 44 |
+
- seed: 42
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_steps: 100
|
| 48 |
+
- num_epochs: 30.0
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:------:|:----:|:---------------:|:------:|
|
| 55 |
+
| 7.3623 | 0.2809 | 100 | 0.9287 | 0.7283 |
|
| 56 |
+
| 0.9213 | 0.5618 | 200 | 0.6511 | 0.5931 |
|
| 57 |
+
| 0.7224 | 0.8427 | 300 | 0.6387 | 0.5434 |
|
| 58 |
+
| 0.7132 | 1.1236 | 400 | 0.6140 | 0.5213 |
|
| 59 |
+
| 0.7195 | 1.4045 | 500 | 0.6097 | 0.5146 |
|
| 60 |
+
| 0.7054 | 1.6854 | 600 | 0.6145 | 0.5126 |
|
| 61 |
+
| 0.7417 | 1.9663 | 700 | 0.6062 | 0.5257 |
|
| 62 |
+
| 0.7029 | 2.2472 | 800 | 0.6022 | 0.4947 |
|
| 63 |
+
| 0.6845 | 2.5281 | 900 | 0.5886 | 0.5023 |
|
| 64 |
+
| 0.663 | 2.8090 | 1000 | 0.5915 | 0.4926 |
|
| 65 |
+
| 0.7129 | 3.0899 | 1100 | 0.5833 | 0.4920 |
|
| 66 |
+
| 0.6735 | 3.3708 | 1200 | 0.5877 | 0.4832 |
|
| 67 |
+
| 0.672 | 3.6517 | 1300 | 0.5863 | 0.5151 |
|
| 68 |
+
| 0.6494 | 3.9326 | 1400 | 0.5795 | 0.4844 |
|
| 69 |
+
| 0.7049 | 4.2135 | 1500 | 0.5724 | 0.4716 |
|
| 70 |
+
| 0.5898 | 4.4944 | 1600 | 0.5640 | 0.4762 |
|
| 71 |
+
| 0.6581 | 4.7753 | 1700 | 0.5582 | 0.4724 |
|
| 72 |
+
| 0.6262 | 5.0562 | 1800 | 0.5447 | 0.4751 |
|
| 73 |
+
| 0.6179 | 5.3371 | 1900 | 0.5497 | 0.4656 |
|
| 74 |
+
| 0.5896 | 5.6180 | 2000 | 0.5444 | 0.4779 |
|
| 75 |
+
| 0.6438 | 5.8989 | 2100 | 0.5399 | 0.4700 |
|
| 76 |
+
| 0.6086 | 6.1798 | 2200 | 0.5520 | 0.4598 |
|
| 77 |
+
| 0.6226 | 6.4607 | 2300 | 0.5386 | 0.4797 |
|
| 78 |
+
| 0.6148 | 6.7416 | 2400 | 0.5574 | 0.4680 |
|
| 79 |
+
| 0.5838 | 7.0225 | 2500 | 0.5497 | 0.4639 |
|
| 80 |
+
| 0.5407 | 7.3034 | 2600 | 0.5377 | 0.4631 |
|
| 81 |
+
| 0.6186 | 7.5843 | 2700 | 0.5404 | 0.4715 |
|
| 82 |
+
| 0.5922 | 7.8652 | 2800 | 0.5381 | 0.4609 |
|
| 83 |
+
| 0.5799 | 8.1461 | 2900 | 0.5312 | 0.4620 |
|
| 84 |
+
| 0.5914 | 8.4270 | 3000 | 0.5309 | 0.4631 |
|
| 85 |
+
| 0.6194 | 8.7079 | 3100 | 0.5317 | 0.4678 |
|
| 86 |
+
| 0.5851 | 8.9888 | 3200 | 0.5389 | 0.4575 |
|
| 87 |
+
| 0.5764 | 9.2697 | 3300 | 0.5579 | 0.4550 |
|
| 88 |
+
|
| 89 |
+
|
| 90 |
+
### Framework versions
|
| 91 |
+
|
| 92 |
+
- Transformers 4.46.0.dev0
|
| 93 |
+
- Pytorch 2.4.1+cu121
|
| 94 |
+
- Datasets 3.0.1
|
| 95 |
+
- Tokenizers 0.20.0
|