update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- wer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: mounir4
|
| 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 |
+
# mounir4
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.6829
|
| 20 |
+
- Wer: 1
|
| 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 |
+
- gradient_accumulation_steps: 4
|
| 44 |
+
- total_train_batch_size: 64
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_steps: 1000
|
| 48 |
+
- training_steps: 10000
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:------:|:-----:|:---------------:|:---:|
|
| 55 |
+
| 3.3494 | 8.51 | 500 | 3.1482 | 1 |
|
| 56 |
+
| 2.9331 | 17.02 | 1000 | 2.9053 | 1 |
|
| 57 |
+
| 2.8691 | 25.53 | 1500 | 2.8793 | 1 |
|
| 58 |
+
| 2.8393 | 34.04 | 2000 | 2.8696 | 1 |
|
| 59 |
+
| 1.9588 | 42.55 | 2500 | 1.5982 | 1 |
|
| 60 |
+
| 0.9108 | 51.06 | 3000 | 0.8335 | 1 |
|
| 61 |
+
| 0.7196 | 59.57 | 3500 | 0.7443 | 1 |
|
| 62 |
+
| 0.6198 | 68.09 | 4000 | 0.6949 | 1 |
|
| 63 |
+
| 0.5558 | 76.6 | 4500 | 0.6862 | 1 |
|
| 64 |
+
| 0.5152 | 85.11 | 5000 | 0.6743 | 1 |
|
| 65 |
+
| 0.4781 | 93.62 | 5500 | 0.6668 | 1 |
|
| 66 |
+
| 0.4442 | 102.13 | 6000 | 0.6587 | 1 |
|
| 67 |
+
| 0.4255 | 110.64 | 6500 | 0.6498 | 1 |
|
| 68 |
+
| 0.408 | 119.15 | 7000 | 0.6698 | 1 |
|
| 69 |
+
| 0.3888 | 127.66 | 7500 | 0.6739 | 1 |
|
| 70 |
+
| 0.3815 | 136.17 | 8000 | 0.6754 | 1 |
|
| 71 |
+
| 0.3704 | 144.68 | 8500 | 0.6843 | 1 |
|
| 72 |
+
| 0.3625 | 153.19 | 9000 | 0.6707 | 1 |
|
| 73 |
+
| 0.356 | 161.7 | 9500 | 0.6812 | 1 |
|
| 74 |
+
| 0.3541 | 170.21 | 10000 | 0.6829 | 1 |
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
### Framework versions
|
| 78 |
+
|
| 79 |
+
- Transformers 4.28.0
|
| 80 |
+
- Pytorch 2.0.1+cu117
|
| 81 |
+
- Datasets 2.12.0
|
| 82 |
+
- Tokenizers 0.13.3
|