update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- ug
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
tags:
|
| 6 |
+
- automatic-speech-recognition
|
| 7 |
+
- mozilla-foundation/common_voice_7_0
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
datasets:
|
| 10 |
+
- common_voice
|
| 11 |
+
model-index:
|
| 12 |
+
- name: uyghur
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# uyghur
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - UG dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.2266
|
| 24 |
+
- Wer: 0.3655
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Intended uses & limitations
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training and evaluation data
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training procedure
|
| 39 |
+
|
| 40 |
+
### Training hyperparameters
|
| 41 |
+
|
| 42 |
+
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 7.5e-05
|
| 44 |
+
- train_batch_size: 8
|
| 45 |
+
- eval_batch_size: 8
|
| 46 |
+
- seed: 42
|
| 47 |
+
- gradient_accumulation_steps: 4
|
| 48 |
+
- total_train_batch_size: 32
|
| 49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
+
- lr_scheduler_type: linear
|
| 51 |
+
- lr_scheduler_warmup_steps: 2000
|
| 52 |
+
- num_epochs: 50.0
|
| 53 |
+
- mixed_precision_training: Native AMP
|
| 54 |
+
|
| 55 |
+
### Training results
|
| 56 |
+
|
| 57 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 58 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 59 |
+
| 3.6863 | 2.73 | 500 | 3.5362 | 1.0 |
|
| 60 |
+
| 3.1409 | 5.46 | 1000 | 3.1328 | 1.0 |
|
| 61 |
+
| 1.8979 | 8.2 | 1500 | 0.9715 | 0.8864 |
|
| 62 |
+
| 1.4859 | 10.93 | 2000 | 0.5234 | 0.7063 |
|
| 63 |
+
| 1.3388 | 13.66 | 2500 | 0.4094 | 0.6203 |
|
| 64 |
+
| 1.2531 | 16.39 | 3000 | 0.3596 | 0.5185 |
|
| 65 |
+
| 1.1992 | 19.13 | 3500 | 0.3221 | 0.4854 |
|
| 66 |
+
| 1.1589 | 21.86 | 4000 | 0.3040 | 0.4610 |
|
| 67 |
+
| 1.1345 | 24.59 | 4500 | 0.2907 | 0.4450 |
|
| 68 |
+
| 1.086 | 27.32 | 5000 | 0.2744 | 0.4299 |
|
| 69 |
+
| 1.0697 | 30.05 | 5500 | 0.2617 | 0.4148 |
|
| 70 |
+
| 1.0518 | 32.79 | 6000 | 0.2563 | 0.4033 |
|
| 71 |
+
| 1.0101 | 35.52 | 6500 | 0.2480 | 0.3934 |
|
| 72 |
+
| 1.0013 | 38.25 | 7000 | 0.2412 | 0.3855 |
|
| 73 |
+
| 0.9845 | 40.98 | 7500 | 0.2397 | 0.3771 |
|
| 74 |
+
| 0.9739 | 43.72 | 8000 | 0.2303 | 0.3726 |
|
| 75 |
+
| 0.9636 | 46.45 | 8500 | 0.2285 | 0.3687 |
|
| 76 |
+
| 0.9466 | 49.18 | 9000 | 0.2261 | 0.3648 |
|
| 77 |
+
|
| 78 |
+
|
| 79 |
+
### Framework versions
|
| 80 |
+
|
| 81 |
+
- Transformers 4.16.0.dev0
|
| 82 |
+
- Pytorch 1.10.1+cu102
|
| 83 |
+
- Datasets 1.18.2.dev0
|
| 84 |
+
- Tokenizers 0.11.0
|