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 |
+
- mir_st500
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: wav2vec2-base-mirst500-ac
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# wav2vec2-base-mirst500-ac
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the mir_st500 dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.7566
|
| 22 |
+
- Accuracy: 0.7570
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 3e-05
|
| 42 |
+
- train_batch_size: 16
|
| 43 |
+
- eval_batch_size: 1
|
| 44 |
+
- seed: 0
|
| 45 |
+
- distributed_type: multi-GPU
|
| 46 |
+
- num_devices: 2
|
| 47 |
+
- gradient_accumulation_steps: 4
|
| 48 |
+
- total_train_batch_size: 128
|
| 49 |
+
- total_eval_batch_size: 2
|
| 50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: linear
|
| 52 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 53 |
+
- num_epochs: 15.0
|
| 54 |
+
- mixed_precision_training: Native AMP
|
| 55 |
+
|
| 56 |
+
### Training results
|
| 57 |
+
|
| 58 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 59 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 60 |
+
| 1.3718 | 1.0 | 1304 | 1.4422 | 0.4255 |
|
| 61 |
+
| 1.1285 | 2.0 | 2608 | 1.1061 | 0.5869 |
|
| 62 |
+
| 1.0275 | 3.0 | 3912 | 0.8825 | 0.6724 |
|
| 63 |
+
| 0.9982 | 4.0 | 5216 | 0.9181 | 0.6713 |
|
| 64 |
+
| 0.9482 | 5.0 | 6520 | 0.8717 | 0.6971 |
|
| 65 |
+
| 0.8687 | 6.0 | 7824 | 0.8041 | 0.7164 |
|
| 66 |
+
| 0.8841 | 7.0 | 9128 | 0.8869 | 0.7034 |
|
| 67 |
+
| 0.8094 | 8.0 | 10432 | 0.8216 | 0.7172 |
|
| 68 |
+
| 0.7733 | 9.0 | 11736 | 0.8018 | 0.7298 |
|
| 69 |
+
| 0.7892 | 10.0 | 13040 | 0.7517 | 0.7426 |
|
| 70 |
+
| 0.8736 | 11.0 | 14344 | 0.7482 | 0.7482 |
|
| 71 |
+
| 0.7035 | 12.0 | 15648 | 0.7730 | 0.7488 |
|
| 72 |
+
| 0.7361 | 13.0 | 16952 | 0.7677 | 0.7510 |
|
| 73 |
+
| 0.7808 | 14.0 | 18256 | 0.7765 | 0.7512 |
|
| 74 |
+
| 0.7359 | 15.0 | 19560 | 0.7566 | 0.7570 |
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
### Framework versions
|
| 78 |
+
|
| 79 |
+
- Transformers 4.18.0
|
| 80 |
+
- Pytorch 1.9.1+cu102
|
| 81 |
+
- Datasets 2.0.0
|
| 82 |
+
- Tokenizers 0.11.6
|