Commit
·
a878d05
1
Parent(s):
b992b77
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- common_voice_11_0
|
| 7 |
+
metrics:
|
| 8 |
+
- wer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: wav2vec2-large-xlsr-53-ur
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Automatic Speech Recognition
|
| 14 |
+
type: automatic-speech-recognition
|
| 15 |
+
dataset:
|
| 16 |
+
name: common_voice_11_0
|
| 17 |
+
type: common_voice_11_0
|
| 18 |
+
config: ur
|
| 19 |
+
split: test
|
| 20 |
+
args: ur
|
| 21 |
+
metrics:
|
| 22 |
+
- name: Wer
|
| 23 |
+
type: wer
|
| 24 |
+
value: 0.4816893775162589
|
| 25 |
+
---
|
| 26 |
+
|
| 27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 28 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 29 |
+
|
| 30 |
+
# wav2vec2-large-xlsr-53-ur
|
| 31 |
+
|
| 32 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the common_voice_11_0 dataset.
|
| 33 |
+
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: inf
|
| 35 |
+
- Wer: 0.4817
|
| 36 |
+
|
| 37 |
+
## Model description
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Intended uses & limitations
|
| 42 |
+
|
| 43 |
+
More information needed
|
| 44 |
+
|
| 45 |
+
## Training and evaluation data
|
| 46 |
+
|
| 47 |
+
More information needed
|
| 48 |
+
|
| 49 |
+
## Training procedure
|
| 50 |
+
|
| 51 |
+
### Training hyperparameters
|
| 52 |
+
|
| 53 |
+
The following hyperparameters were used during training:
|
| 54 |
+
- learning_rate: 0.0003
|
| 55 |
+
- train_batch_size: 6
|
| 56 |
+
- eval_batch_size: 6
|
| 57 |
+
- seed: 42
|
| 58 |
+
- distributed_type: multi-GPU
|
| 59 |
+
- num_devices: 2
|
| 60 |
+
- total_train_batch_size: 12
|
| 61 |
+
- total_eval_batch_size: 12
|
| 62 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 63 |
+
- lr_scheduler_type: linear
|
| 64 |
+
- lr_scheduler_warmup_steps: 500
|
| 65 |
+
- num_epochs: 15.0
|
| 66 |
+
- mixed_precision_training: Native AMP
|
| 67 |
+
|
| 68 |
+
### Training results
|
| 69 |
+
|
| 70 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 71 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 72 |
+
| 3.0981 | 0.48 | 300 | inf | 0.9981 |
|
| 73 |
+
| 2.0031 | 0.97 | 600 | inf | 0.8283 |
|
| 74 |
+
| 0.7476 | 1.45 | 900 | inf | 0.6584 |
|
| 75 |
+
| 0.8585 | 1.94 | 1200 | inf | 0.5823 |
|
| 76 |
+
| 0.4978 | 2.42 | 1500 | inf | 0.5564 |
|
| 77 |
+
| 0.5423 | 2.9 | 1800 | inf | 0.5209 |
|
| 78 |
+
| 0.3504 | 3.39 | 2100 | inf | 0.5396 |
|
| 79 |
+
| 0.3185 | 3.87 | 2400 | inf | 0.4865 |
|
| 80 |
+
| 0.3337 | 4.35 | 2700 | inf | 0.4733 |
|
| 81 |
+
| 0.4935 | 4.84 | 3000 | inf | 0.4721 |
|
| 82 |
+
| 0.4022 | 5.32 | 3300 | inf | 0.4692 |
|
| 83 |
+
| 0.3517 | 5.81 | 3600 | inf | 0.4585 |
|
| 84 |
+
| 0.1838 | 6.29 | 3900 | inf | 0.4567 |
|
| 85 |
+
| 0.2635 | 6.77 | 4200 | inf | 0.4459 |
|
| 86 |
+
| 0.1163 | 7.26 | 4500 | inf | 0.4495 |
|
| 87 |
+
| 0.1776 | 7.74 | 4800 | inf | 0.4657 |
|
| 88 |
+
| 0.262 | 8.23 | 5100 | inf | 0.4562 |
|
| 89 |
+
| 0.1853 | 8.71 | 5400 | inf | 0.4724 |
|
| 90 |
+
| 0.3173 | 9.19 | 5700 | inf | 0.4752 |
|
| 91 |
+
| 0.4985 | 9.68 | 6000 | inf | 0.4604 |
|
| 92 |
+
| 0.3707 | 10.16 | 6300 | inf | 0.4769 |
|
| 93 |
+
| 0.4214 | 10.65 | 6600 | inf | 0.5246 |
|
| 94 |
+
| 0.3443 | 11.13 | 6900 | inf | 0.5391 |
|
| 95 |
+
| 0.3302 | 11.61 | 7200 | inf | 0.5051 |
|
| 96 |
+
| 0.327 | 12.1 | 7500 | inf | 0.5389 |
|
| 97 |
+
| 0.2489 | 12.58 | 7800 | inf | 0.5355 |
|
| 98 |
+
| 0.2328 | 13.06 | 8100 | inf | 0.5111 |
|
| 99 |
+
| 0.2488 | 13.55 | 8400 | inf | 0.4794 |
|
| 100 |
+
| 0.3255 | 14.03 | 8700 | inf | 0.4959 |
|
| 101 |
+
| 0.3056 | 14.52 | 9000 | inf | 0.4895 |
|
| 102 |
+
| 0.1758 | 15.0 | 9300 | inf | 0.4817 |
|
| 103 |
+
|
| 104 |
+
|
| 105 |
+
### Framework versions
|
| 106 |
+
|
| 107 |
+
- Transformers 4.27.0.dev0
|
| 108 |
+
- Pytorch 1.13.1+cu116
|
| 109 |
+
- Datasets 2.9.0
|
| 110 |
+
- Tokenizers 0.13.2
|