update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: working
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# working
|
| 14 |
+
|
| 15 |
+
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.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.2584
|
| 18 |
+
- Wer: 0.6024
|
| 19 |
+
- Cer: 0.0723
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 3e-05
|
| 39 |
+
- train_batch_size: 2
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 2
|
| 43 |
+
- total_train_batch_size: 4
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- lr_scheduler_warmup_steps: 2000
|
| 47 |
+
- training_steps: 70000
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 53 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
|
| 54 |
+
| 2.0401 | 1.49 | 1000 | 1.3913 | 0.9911 | 0.4127 |
|
| 55 |
+
| 1.2772 | 2.98 | 2000 | 0.4117 | 0.7644 | 0.1036 |
|
| 56 |
+
| 1.0861 | 4.46 | 3000 | 0.3281 | 0.6962 | 0.0868 |
|
| 57 |
+
| 1.0803 | 5.95 | 4000 | 0.2970 | 0.6645 | 0.0796 |
|
| 58 |
+
| 1.0256 | 7.44 | 5000 | 0.2986 | 0.6556 | 0.0820 |
|
| 59 |
+
| 0.9536 | 8.93 | 6000 | 0.2873 | 0.6418 | 0.0767 |
|
| 60 |
+
| 0.9154 | 10.42 | 7000 | 0.3896 | 0.6450 | 0.0812 |
|
| 61 |
+
| 0.9187 | 11.9 | 8000 | 0.2946 | 0.6239 | 0.0771 |
|
| 62 |
+
| 0.8693 | 13.39 | 9000 | 0.2655 | 0.6093 | 0.0746 |
|
| 63 |
+
| 0.8335 | 14.88 | 10000 | 0.2797 | 0.6052 | 0.0764 |
|
| 64 |
+
| 0.8461 | 16.37 | 11000 | 0.2879 | 0.6231 | 0.0766 |
|
| 65 |
+
| 0.8363 | 17.86 | 12000 | 0.2616 | 0.6052 | 0.0726 |
|
| 66 |
+
| 0.796 | 19.35 | 13000 | 0.2656 | 0.6109 | 0.0740 |
|
| 67 |
+
| 0.8136 | 20.83 | 14000 | 0.2773 | 0.6255 | 0.0747 |
|
| 68 |
+
| 0.7319 | 22.32 | 15000 | 0.2770 | 0.6214 | 0.0748 |
|
| 69 |
+
| 0.7428 | 23.81 | 16000 | 0.2697 | 0.6052 | 0.0746 |
|
| 70 |
+
| 0.7264 | 25.3 | 17000 | 0.2716 | 0.5971 | 0.0733 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.17.0
|
| 76 |
+
- Pytorch 2.4.0
|
| 77 |
+
- Datasets 3.0.1
|
| 78 |
+
- Tokenizers 0.20.0
|