Commit
•
cd22b0a
1
Parent(s):
3cc4dde
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 |
+
datasets:
|
| 6 |
+
- common_voice
|
| 7 |
+
model-index:
|
| 8 |
+
- name: ''
|
| 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 |
+
#
|
| 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: 0.7181
|
| 20 |
+
- Wer: 0.459
|
| 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: 0.000222
|
| 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: 1000
|
| 48 |
+
- num_epochs: 150.0
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:------:|:----:|:---------------:|:------:|
|
| 55 |
+
| 9.6799 | 9.09 | 200 | 3.6119 | 1.0 |
|
| 56 |
+
| 3.1332 | 18.18 | 400 | 2.5352 | 1.005 |
|
| 57 |
+
| 1.0465 | 27.27 | 600 | 0.6169 | 0.682 |
|
| 58 |
+
| 0.3452 | 36.36 | 800 | 0.6572 | 0.607 |
|
| 59 |
+
| 0.2575 | 45.44 | 1000 | 0.6527 | 0.578 |
|
| 60 |
+
| 0.2088 | 54.53 | 1200 | 0.6828 | 0.551 |
|
| 61 |
+
| 0.158 | 63.62 | 1400 | 0.7074 | 0.5575 |
|
| 62 |
+
| 0.1309 | 72.71 | 1600 | 0.6523 | 0.5595 |
|
| 63 |
+
| 0.1074 | 81.8 | 1800 | 0.7262 | 0.5415 |
|
| 64 |
+
| 0.087 | 90.89 | 2000 | 0.7199 | 0.521 |
|
| 65 |
+
| 0.0711 | 99.98 | 2200 | 0.7113 | 0.523 |
|
| 66 |
+
| 0.0601 | 109.09 | 2400 | 0.6863 | 0.496 |
|
| 67 |
+
| 0.0451 | 118.18 | 2600 | 0.6998 | 0.483 |
|
| 68 |
+
| 0.0378 | 127.27 | 2800 | 0.6971 | 0.4615 |
|
| 69 |
+
| 0.0319 | 136.36 | 3000 | 0.7119 | 0.4475 |
|
| 70 |
+
| 0.0305 | 145.44 | 3200 | 0.7181 | 0.459 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.17.0.dev0
|
| 76 |
+
- Pytorch 1.10.2+cu102
|
| 77 |
+
- Datasets 1.18.2.dev0
|
| 78 |
+
- Tokenizers 0.11.0
|