update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
datasets:
|
| 5 |
+
- superb
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: trillsson3-ft-keyword-spotting-13
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# trillsson3-ft-keyword-spotting-13
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [vumichien/nonsemantic-speech-trillsson3](https://huggingface.co/vumichien/nonsemantic-speech-trillsson3) on the superb dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.3101
|
| 21 |
+
- Accuracy: 0.9114
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 0.0003
|
| 41 |
+
- train_batch_size: 16
|
| 42 |
+
- eval_batch_size: 32
|
| 43 |
+
- seed: 0
|
| 44 |
+
- gradient_accumulation_steps: 4
|
| 45 |
+
- total_train_batch_size: 64
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
+
- num_epochs: 20.0
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 55 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 56 |
+
| 1.8064 | 1.0 | 798 | 0.9359 | 0.6403 |
|
| 57 |
+
| 0.8601 | 2.0 | 1596 | 0.4832 | 0.8528 |
|
| 58 |
+
| 0.7585 | 3.0 | 2394 | 0.3952 | 0.8854 |
|
| 59 |
+
| 0.7026 | 4.0 | 3192 | 0.3623 | 0.9050 |
|
| 60 |
+
| 0.6924 | 5.0 | 3990 | 0.3456 | 0.9035 |
|
| 61 |
+
| 0.6816 | 6.0 | 4788 | 0.3405 | 0.9006 |
|
| 62 |
+
| 0.6461 | 7.0 | 5586 | 0.3384 | 0.9004 |
|
| 63 |
+
| 0.6697 | 8.0 | 6384 | 0.3272 | 0.9045 |
|
| 64 |
+
| 0.6575 | 9.0 | 7182 | 0.3237 | 0.9109 |
|
| 65 |
+
| 0.6634 | 10.0 | 7980 | 0.3258 | 0.9026 |
|
| 66 |
+
| 0.6604 | 11.0 | 8778 | 0.3179 | 0.9042 |
|
| 67 |
+
| 0.6483 | 12.0 | 9576 | 0.3203 | 0.9059 |
|
| 68 |
+
| 0.6578 | 13.0 | 10374 | 0.3160 | 0.9089 |
|
| 69 |
+
| 0.654 | 14.0 | 11172 | 0.3139 | 0.9091 |
|
| 70 |
+
| 0.6418 | 15.0 | 11970 | 0.3091 | 0.9125 |
|
| 71 |
+
| 0.6394 | 16.0 | 12768 | 0.3223 | 0.9029 |
|
| 72 |
+
| 0.637 | 17.0 | 13566 | 0.3085 | 0.9153 |
|
| 73 |
+
| 0.6258 | 18.0 | 14364 | 0.3182 | 0.9069 |
|
| 74 |
+
| 0.6438 | 19.0 | 15162 | 0.3127 | 0.9078 |
|
| 75 |
+
| 0.6569 | 20.0 | 15960 | 0.3101 | 0.9114 |
|
| 76 |
+
|
| 77 |
+
|
| 78 |
+
### Framework versions
|
| 79 |
+
|
| 80 |
+
- Transformers 4.23.0.dev0
|
| 81 |
+
- Pytorch 1.12.1+cu113
|
| 82 |
+
- Datasets 2.6.1
|
| 83 |
+
- Tokenizers 0.13.1
|