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-11
|
| 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-11
|
| 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: 0.3166
|
| 21 |
+
- Accuracy: 0.9088
|
| 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: 32
|
| 42 |
+
- eval_batch_size: 32
|
| 43 |
+
- seed: 0
|
| 44 |
+
- gradient_accumulation_steps: 4
|
| 45 |
+
- total_train_batch_size: 128
|
| 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 |
+
| 2.9219 | 1.0 | 399 | 1.2023 | 0.6217 |
|
| 57 |
+
| 0.9604 | 2.0 | 798 | 0.5437 | 0.8117 |
|
| 58 |
+
| 0.7608 | 3.0 | 1197 | 0.4222 | 0.8888 |
|
| 59 |
+
| 0.7045 | 4.0 | 1596 | 0.3881 | 0.8932 |
|
| 60 |
+
| 0.659 | 5.0 | 1995 | 0.3706 | 0.8847 |
|
| 61 |
+
| 0.6541 | 6.0 | 2394 | 0.3553 | 0.8917 |
|
| 62 |
+
| 0.6448 | 7.0 | 2793 | 0.3482 | 0.8953 |
|
| 63 |
+
| 0.6288 | 8.0 | 3192 | 0.3409 | 0.8989 |
|
| 64 |
+
| 0.641 | 9.0 | 3591 | 0.3297 | 0.9051 |
|
| 65 |
+
| 0.6369 | 10.0 | 3990 | 0.3325 | 0.9042 |
|
| 66 |
+
| 0.6218 | 11.0 | 4389 | 0.3250 | 0.9064 |
|
| 67 |
+
| 0.6247 | 12.0 | 4788 | 0.3312 | 0.8959 |
|
| 68 |
+
| 0.6284 | 13.0 | 5187 | 0.3217 | 0.9069 |
|
| 69 |
+
| 0.6213 | 14.0 | 5586 | 0.3301 | 0.8978 |
|
| 70 |
+
| 0.6274 | 15.0 | 5985 | 0.3180 | 0.9081 |
|
| 71 |
+
| 0.627 | 16.0 | 6384 | 0.3257 | 0.9020 |
|
| 72 |
+
| 0.6227 | 17.0 | 6783 | 0.3193 | 0.9056 |
|
| 73 |
+
| 0.6192 | 18.0 | 7182 | 0.3199 | 0.9066 |
|
| 74 |
+
| 0.6075 | 19.0 | 7581 | 0.3183 | 0.9073 |
|
| 75 |
+
| 0.6196 | 20.0 | 7980 | 0.3166 | 0.9088 |
|
| 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
|