Commit
·
619707e
1
Parent(s):
5d26ffe
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-bg-d2
|
| 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-bg-d2
|
| 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: 0.3421
|
| 20 |
+
- Wer: 0.2860
|
| 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: 0.00025
|
| 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: 700
|
| 48 |
+
- num_epochs: 35
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 55 |
+
| 6.8791 | 1.74 | 200 | 3.1902 | 1.0 |
|
| 56 |
+
| 3.0441 | 3.48 | 400 | 2.8098 | 0.9864 |
|
| 57 |
+
| 1.1499 | 5.22 | 600 | 0.4668 | 0.5014 |
|
| 58 |
+
| 0.4968 | 6.96 | 800 | 0.4162 | 0.4472 |
|
| 59 |
+
| 0.3553 | 8.7 | 1000 | 0.3580 | 0.3777 |
|
| 60 |
+
| 0.3027 | 10.43 | 1200 | 0.3422 | 0.3506 |
|
| 61 |
+
| 0.2562 | 12.17 | 1400 | 0.3556 | 0.3639 |
|
| 62 |
+
| 0.2272 | 13.91 | 1600 | 0.3621 | 0.3583 |
|
| 63 |
+
| 0.2125 | 15.65 | 1800 | 0.3436 | 0.3358 |
|
| 64 |
+
| 0.1904 | 17.39 | 2000 | 0.3650 | 0.3545 |
|
| 65 |
+
| 0.1695 | 19.13 | 2200 | 0.3366 | 0.3241 |
|
| 66 |
+
| 0.1532 | 20.87 | 2400 | 0.3550 | 0.3311 |
|
| 67 |
+
| 0.1453 | 22.61 | 2600 | 0.3582 | 0.3131 |
|
| 68 |
+
| 0.1359 | 24.35 | 2800 | 0.3524 | 0.3084 |
|
| 69 |
+
| 0.1233 | 26.09 | 3000 | 0.3503 | 0.2973 |
|
| 70 |
+
| 0.1114 | 27.83 | 3200 | 0.3434 | 0.2946 |
|
| 71 |
+
| 0.1051 | 29.57 | 3400 | 0.3474 | 0.2956 |
|
| 72 |
+
| 0.0965 | 31.3 | 3600 | 0.3426 | 0.2907 |
|
| 73 |
+
| 0.0923 | 33.04 | 3800 | 0.3478 | 0.2894 |
|
| 74 |
+
| 0.0894 | 34.78 | 4000 | 0.3421 | 0.2860 |
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
### Framework versions
|
| 78 |
+
|
| 79 |
+
- Transformers 4.16.2
|
| 80 |
+
- Pytorch 1.10.0+cu111
|
| 81 |
+
- Datasets 1.18.3
|
| 82 |
+
- Tokenizers 0.11.0
|