Commit
•
180d66b
1
Parent(s):
8f6111c
End of training
Browse files- README.md +98 -0
- pytorch_model.bin +1 -1
README.md
ADDED
|
@@ -0,0 +1,98 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: facebook/wav2vec2-xls-r-300m
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- wer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: wav2vec2_XLSR_darija_maroc
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# wav2vec2_XLSR_darija_maroc
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.2860
|
| 21 |
+
- Wer: 0.3290
|
| 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: 0.0003
|
| 41 |
+
- train_batch_size: 16
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 2
|
| 45 |
+
- total_train_batch_size: 32
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- lr_scheduler_warmup_steps: 500
|
| 49 |
+
- num_epochs: 30
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
| 55 |
+
| 4.9354 | 0.83 | 400 | 2.0492 | 1.0371 |
|
| 56 |
+
| 0.8236 | 1.66 | 800 | 0.4434 | 0.5832 |
|
| 57 |
+
| 0.4821 | 2.49 | 1200 | 0.3597 | 0.5114 |
|
| 58 |
+
| 0.3823 | 3.32 | 1600 | 0.3265 | 0.4758 |
|
| 59 |
+
| 0.3231 | 4.15 | 2000 | 0.3149 | 0.4526 |
|
| 60 |
+
| 0.2854 | 4.97 | 2400 | 0.2797 | 0.4237 |
|
| 61 |
+
| 0.2529 | 5.8 | 2800 | 0.3027 | 0.4415 |
|
| 62 |
+
| 0.2493 | 6.63 | 3200 | 0.2926 | 0.4264 |
|
| 63 |
+
| 0.2138 | 7.46 | 3600 | 0.2857 | 0.4169 |
|
| 64 |
+
| 0.2067 | 8.29 | 4000 | 0.2743 | 0.4099 |
|
| 65 |
+
| 0.1898 | 9.12 | 4400 | 0.2798 | 0.3993 |
|
| 66 |
+
| 0.1755 | 9.95 | 4800 | 0.2800 | 0.3913 |
|
| 67 |
+
| 0.1603 | 10.78 | 5200 | 0.2709 | 0.3860 |
|
| 68 |
+
| 0.1608 | 11.61 | 5600 | 0.2716 | 0.3872 |
|
| 69 |
+
| 0.1462 | 12.44 | 6000 | 0.2697 | 0.3825 |
|
| 70 |
+
| 0.137 | 13.26 | 6400 | 0.2855 | 0.3819 |
|
| 71 |
+
| 0.1326 | 14.09 | 6800 | 0.2860 | 0.3733 |
|
| 72 |
+
| 0.123 | 14.92 | 7200 | 0.2677 | 0.3813 |
|
| 73 |
+
| 0.1168 | 15.75 | 7600 | 0.2780 | 0.3740 |
|
| 74 |
+
| 0.1113 | 16.58 | 8000 | 0.2926 | 0.3719 |
|
| 75 |
+
| 0.1057 | 17.41 | 8400 | 0.2927 | 0.3704 |
|
| 76 |
+
| 0.0996 | 18.24 | 8800 | 0.2825 | 0.3602 |
|
| 77 |
+
| 0.0967 | 19.07 | 9200 | 0.2983 | 0.3641 |
|
| 78 |
+
| 0.0925 | 19.9 | 9600 | 0.2843 | 0.3576 |
|
| 79 |
+
| 0.0894 | 20.73 | 10000 | 0.2726 | 0.3668 |
|
| 80 |
+
| 0.0836 | 21.55 | 10400 | 0.2829 | 0.3560 |
|
| 81 |
+
| 0.0789 | 22.38 | 10800 | 0.2806 | 0.3508 |
|
| 82 |
+
| 0.0778 | 23.21 | 11200 | 0.2849 | 0.3540 |
|
| 83 |
+
| 0.0742 | 24.04 | 11600 | 0.2770 | 0.3436 |
|
| 84 |
+
| 0.0679 | 24.87 | 12000 | 0.2850 | 0.3425 |
|
| 85 |
+
| 0.063 | 25.7 | 12400 | 0.2846 | 0.3366 |
|
| 86 |
+
| 0.0593 | 26.53 | 12800 | 0.2811 | 0.3351 |
|
| 87 |
+
| 0.0586 | 27.36 | 13200 | 0.2863 | 0.3322 |
|
| 88 |
+
| 0.0555 | 28.19 | 13600 | 0.2819 | 0.3311 |
|
| 89 |
+
| 0.053 | 29.02 | 14000 | 0.2874 | 0.3301 |
|
| 90 |
+
| 0.0498 | 29.84 | 14400 | 0.2860 | 0.3290 |
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
### Framework versions
|
| 94 |
+
|
| 95 |
+
- Transformers 4.34.1
|
| 96 |
+
- Pytorch 2.1.0+cu118
|
| 97 |
+
- Datasets 2.14.6
|
| 98 |
+
- Tokenizers 0.14.1
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262049962
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf1fe4f15e7b3b48097efd8ecffcee04c2ab9a65b6c86c89ffc58edc88dca4d0
|
| 3 |
size 1262049962
|