Commit
•
e7b9cbc
1
Parent(s):
22360e4
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,106 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- xtreme_s
|
| 7 |
+
metrics:
|
| 8 |
+
- f1
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: xtreme_s_w2v2_minds14.en-US
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
# xtreme_s_w2v2_minds14.en-US
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-lv60](https://huggingface.co/facebook/wav2vec2-large-lv60) on the xtreme_s dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.5337
|
| 23 |
+
- F1: 0.9144
|
| 24 |
+
- Accuracy: 0.9113
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Intended uses & limitations
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training and evaluation data
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training procedure
|
| 39 |
+
|
| 40 |
+
### Training hyperparameters
|
| 41 |
+
|
| 42 |
+
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 0.0003
|
| 44 |
+
- train_batch_size: 2
|
| 45 |
+
- eval_batch_size: 8
|
| 46 |
+
- seed: 42
|
| 47 |
+
- distributed_type: multi-GPU
|
| 48 |
+
- num_devices: 2
|
| 49 |
+
- gradient_accumulation_steps: 8
|
| 50 |
+
- total_train_batch_size: 32
|
| 51 |
+
- total_eval_batch_size: 16
|
| 52 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 53 |
+
- lr_scheduler_type: linear
|
| 54 |
+
- lr_scheduler_warmup_steps: 100
|
| 55 |
+
- num_epochs: 150.0
|
| 56 |
+
- mixed_precision_training: Native AMP
|
| 57 |
+
|
| 58 |
+
### Training results
|
| 59 |
+
|
| 60 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy |
|
| 61 |
+
|:-------------:|:------:|:----:|:---------------:|:------:|:--------:|
|
| 62 |
+
| 2.6482 | 3.95 | 20 | 2.6421 | 0.0242 | 0.0745 |
|
| 63 |
+
| 2.6292 | 7.95 | 40 | 2.6359 | 0.0108 | 0.0816 |
|
| 64 |
+
| 2.5993 | 11.95 | 60 | 2.6301 | 0.0167 | 0.0674 |
|
| 65 |
+
| 2.4023 | 15.95 | 80 | 2.5514 | 0.1105 | 0.1454 |
|
| 66 |
+
| 1.4015 | 19.95 | 100 | 1.6843 | 0.5599 | 0.5851 |
|
| 67 |
+
| 0.4379 | 23.95 | 120 | 0.8126 | 0.7921 | 0.7908 |
|
| 68 |
+
| 0.0642 | 27.95 | 140 | 0.7178 | 0.8158 | 0.8156 |
|
| 69 |
+
| 0.0376 | 31.95 | 160 | 0.7286 | 0.8473 | 0.8475 |
|
| 70 |
+
| 0.0185 | 35.95 | 180 | 0.6779 | 0.8719 | 0.8723 |
|
| 71 |
+
| 0.0752 | 39.95 | 200 | 0.7096 | 0.8578 | 0.8511 |
|
| 72 |
+
| 0.0266 | 43.95 | 220 | 0.7655 | 0.8596 | 0.8546 |
|
| 73 |
+
| 0.0078 | 47.95 | 240 | 0.7623 | 0.8563 | 0.8511 |
|
| 74 |
+
| 0.007 | 51.95 | 260 | 0.6620 | 0.8794 | 0.8759 |
|
| 75 |
+
| 0.0047 | 55.95 | 280 | 0.5936 | 0.9045 | 0.9007 |
|
| 76 |
+
| 0.0067 | 59.95 | 300 | 0.8279 | 0.8546 | 0.8617 |
|
| 77 |
+
| 0.0394 | 63.95 | 320 | 0.8766 | 0.8359 | 0.8227 |
|
| 78 |
+
| 0.0051 | 67.95 | 340 | 0.8097 | 0.8483 | 0.8475 |
|
| 79 |
+
| 0.0095 | 71.95 | 360 | 0.6095 | 0.9083 | 0.9078 |
|
| 80 |
+
| 0.0026 | 75.95 | 380 | 0.5286 | 0.8889 | 0.8865 |
|
| 81 |
+
| 0.0023 | 79.95 | 400 | 0.7218 | 0.8926 | 0.8936 |
|
| 82 |
+
| 0.0023 | 83.95 | 420 | 0.6551 | 0.8997 | 0.8972 |
|
| 83 |
+
| 0.0027 | 87.95 | 440 | 0.6664 | 0.8848 | 0.8794 |
|
| 84 |
+
| 0.0019 | 91.95 | 460 | 0.5344 | 0.9032 | 0.9043 |
|
| 85 |
+
| 0.002 | 95.95 | 480 | 0.5863 | 0.8983 | 0.9007 |
|
| 86 |
+
| 0.0015 | 99.95 | 500 | 0.5715 | 0.9047 | 0.9043 |
|
| 87 |
+
| 0.0016 | 103.95 | 520 | 0.5615 | 0.8956 | 0.8936 |
|
| 88 |
+
| 0.0014 | 107.95 | 540 | 0.6353 | 0.8965 | 0.8936 |
|
| 89 |
+
| 0.0014 | 111.95 | 560 | 0.5593 | 0.9041 | 0.9007 |
|
| 90 |
+
| 0.0013 | 115.95 | 580 | 0.6041 | 0.8977 | 0.8936 |
|
| 91 |
+
| 0.0013 | 119.95 | 600 | 0.5794 | 0.9026 | 0.9007 |
|
| 92 |
+
| 0.0012 | 123.95 | 620 | 0.6858 | 0.9003 | 0.8972 |
|
| 93 |
+
| 0.0013 | 127.95 | 640 | 0.6730 | 0.9002 | 0.8972 |
|
| 94 |
+
| 0.0013 | 131.95 | 660 | 0.5707 | 0.9146 | 0.9113 |
|
| 95 |
+
| 0.0012 | 135.95 | 680 | 0.5604 | 0.9153 | 0.9113 |
|
| 96 |
+
| 0.0019 | 139.95 | 700 | 0.5468 | 0.9114 | 0.9078 |
|
| 97 |
+
| 0.0015 | 143.95 | 720 | 0.5361 | 0.9144 | 0.9113 |
|
| 98 |
+
| 0.0012 | 147.95 | 740 | 0.5337 | 0.9144 | 0.9113 |
|
| 99 |
+
|
| 100 |
+
|
| 101 |
+
### Framework versions
|
| 102 |
+
|
| 103 |
+
- Transformers 4.18.0
|
| 104 |
+
- Pytorch 1.11.0+cu113
|
| 105 |
+
- Datasets 2.1.0
|
| 106 |
+
- Tokenizers 0.12.1
|