update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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: 45.7297
|
| 20 |
+
- Wer: 1.0
|
| 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: 8
|
| 41 |
+
- eval_batch_size: 1
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 2
|
| 44 |
+
- total_train_batch_size: 16
|
| 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: 1.0
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:---:|
|
| 55 |
+
| No log | 0.05 | 10 | 239.0014 | 1.0 |
|
| 56 |
+
| No log | 0.1 | 20 | 235.8207 | 1.0 |
|
| 57 |
+
| No log | 0.15 | 30 | 226.9009 | 1.0 |
|
| 58 |
+
| No log | 0.21 | 40 | 198.0769 | 1.0 |
|
| 59 |
+
| No log | 0.26 | 50 | 166.6728 | 1.0 |
|
| 60 |
+
| No log | 0.31 | 60 | 149.1445 | 1.0 |
|
| 61 |
+
| No log | 0.36 | 70 | 138.4403 | 1.0 |
|
| 62 |
+
| No log | 0.41 | 80 | 131.7249 | 1.0 |
|
| 63 |
+
| No log | 0.46 | 90 | 125.5583 | 1.0 |
|
| 64 |
+
| No log | 0.51 | 100 | 119.7515 | 1.0 |
|
| 65 |
+
| No log | 0.56 | 110 | 113.7283 | 1.0 |
|
| 66 |
+
| No log | 0.62 | 120 | 107.2455 | 1.0 |
|
| 67 |
+
| No log | 0.67 | 130 | 100.2172 | 1.0 |
|
| 68 |
+
| No log | 0.72 | 140 | 92.5585 | 1.0 |
|
| 69 |
+
| No log | 0.77 | 150 | 84.2573 | 1.0 |
|
| 70 |
+
| No log | 0.82 | 160 | 75.2953 | 1.0 |
|
| 71 |
+
| No log | 0.87 | 170 | 65.6953 | 1.0 |
|
| 72 |
+
| No log | 0.92 | 180 | 55.7544 | 1.0 |
|
| 73 |
+
| No log | 0.97 | 190 | 45.7297 | 1.0 |
|
| 74 |
+
|
| 75 |
+
|
| 76 |
+
### Framework versions
|
| 77 |
+
|
| 78 |
+
- Transformers 4.17.0.dev0
|
| 79 |
+
- Pytorch 1.10.2+cu102
|
| 80 |
+
- Datasets 1.18.3
|
| 81 |
+
- Tokenizers 0.11.0
|