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 |
+
datasets:
|
| 6 |
+
- common_voice
|
| 7 |
+
model-index:
|
| 8 |
+
- name: wav2vec2-large-xls-r-300m-kika5_my-colab
|
| 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 |
+
# wav2vec2-large-xls-r-300m-kika5_my-colab
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.3860
|
| 20 |
+
- Wer: 0.3505
|
| 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: 0.0003
|
| 40 |
+
- train_batch_size: 16
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 2
|
| 44 |
+
- total_train_batch_size: 32
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_steps: 500
|
| 48 |
+
- num_epochs: 100
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 55 |
+
| 4.0007 | 4.82 | 400 | 0.6696 | 0.8283 |
|
| 56 |
+
| 0.2774 | 9.64 | 800 | 0.4231 | 0.5476 |
|
| 57 |
+
| 0.1182 | 14.46 | 1200 | 0.4253 | 0.5102 |
|
| 58 |
+
| 0.0859 | 19.28 | 1600 | 0.4600 | 0.4866 |
|
| 59 |
+
| 0.0693 | 24.1 | 2000 | 0.4030 | 0.4533 |
|
| 60 |
+
| 0.0611 | 28.92 | 2400 | 0.4189 | 0.4412 |
|
| 61 |
+
| 0.0541 | 33.73 | 2800 | 0.4272 | 0.4380 |
|
| 62 |
+
| 0.0478 | 38.55 | 3200 | 0.4537 | 0.4505 |
|
| 63 |
+
| 0.0428 | 43.37 | 3600 | 0.4349 | 0.4181 |
|
| 64 |
+
| 0.038 | 48.19 | 4000 | 0.4562 | 0.4199 |
|
| 65 |
+
| 0.0345 | 53.01 | 4400 | 0.4209 | 0.4310 |
|
| 66 |
+
| 0.0316 | 57.83 | 4800 | 0.4336 | 0.4058 |
|
| 67 |
+
| 0.0288 | 62.65 | 5200 | 0.4004 | 0.3920 |
|
| 68 |
+
| 0.025 | 67.47 | 5600 | 0.4115 | 0.3857 |
|
| 69 |
+
| 0.0225 | 72.29 | 6000 | 0.4296 | 0.3948 |
|
| 70 |
+
| 0.0182 | 77.11 | 6400 | 0.3963 | 0.3772 |
|
| 71 |
+
| 0.0165 | 81.93 | 6800 | 0.3921 | 0.3687 |
|
| 72 |
+
| 0.0152 | 86.75 | 7200 | 0.3969 | 0.3592 |
|
| 73 |
+
| 0.0133 | 91.57 | 7600 | 0.3803 | 0.3527 |
|
| 74 |
+
| 0.0118 | 96.39 | 8000 | 0.3860 | 0.3505 |
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
### Framework versions
|
| 78 |
+
|
| 79 |
+
- Transformers 4.15.0
|
| 80 |
+
- Pytorch 1.10.0+cu111
|
| 81 |
+
- Datasets 1.17.0
|
| 82 |
+
- Tokenizers 0.10.3
|