End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: facebook/wav2vec2-base
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
datasets:
|
| 8 |
+
- danavery/urbansound8K
|
| 9 |
+
metrics:
|
| 10 |
+
- accuracy
|
| 11 |
+
- f1
|
| 12 |
+
model-index:
|
| 13 |
+
- name: wav2vec2-finetuned-urbansound8k
|
| 14 |
+
results:
|
| 15 |
+
- task:
|
| 16 |
+
name: Audio Classification
|
| 17 |
+
type: audio-classification
|
| 18 |
+
dataset:
|
| 19 |
+
name: URBAN-SOUND8K
|
| 20 |
+
type: danavery/urbansound8K
|
| 21 |
+
args: audio-classification
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Accuracy
|
| 24 |
+
type: accuracy
|
| 25 |
+
value: 0.9650829994275901
|
| 26 |
+
- name: F1
|
| 27 |
+
type: f1
|
| 28 |
+
value: 0.965058831730144
|
| 29 |
+
---
|
| 30 |
+
|
| 31 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 32 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 33 |
+
|
| 34 |
+
# wav2vec2-finetuned-urbansound8k
|
| 35 |
+
|
| 36 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the URBAN-SOUND8K dataset.
|
| 37 |
+
It achieves the following results on the evaluation set:
|
| 38 |
+
- Loss: 0.2672
|
| 39 |
+
- Accuracy: 0.9651
|
| 40 |
+
- F1: 0.9651
|
| 41 |
+
|
| 42 |
+
## Model description
|
| 43 |
+
|
| 44 |
+
More information needed
|
| 45 |
+
|
| 46 |
+
## Intended uses & limitations
|
| 47 |
+
|
| 48 |
+
More information needed
|
| 49 |
+
|
| 50 |
+
## Training and evaluation data
|
| 51 |
+
|
| 52 |
+
More information needed
|
| 53 |
+
|
| 54 |
+
## Training procedure
|
| 55 |
+
|
| 56 |
+
### Training hyperparameters
|
| 57 |
+
|
| 58 |
+
The following hyperparameters were used during training:
|
| 59 |
+
- learning_rate: 3e-05
|
| 60 |
+
- train_batch_size: 4
|
| 61 |
+
- eval_batch_size: 4
|
| 62 |
+
- seed: 42
|
| 63 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 64 |
+
- lr_scheduler_type: linear
|
| 65 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 66 |
+
- num_epochs: 8
|
| 67 |
+
|
| 68 |
+
### Training results
|
| 69 |
+
|
| 70 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
| 71 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|
|
| 72 |
+
| 0.6296 | 1.0 | 1747 | 0.9168 | 0.7098 | 0.6543 |
|
| 73 |
+
| 0.3658 | 2.0 | 3494 | 0.4589 | 0.8798 | 0.8788 |
|
| 74 |
+
| 0.108 | 3.0 | 5241 | 0.4362 | 0.9107 | 0.9102 |
|
| 75 |
+
| 0.3019 | 4.0 | 6988 | 0.4455 | 0.9216 | 0.9215 |
|
| 76 |
+
| 0.0019 | 5.0 | 8735 | 0.3645 | 0.9433 | 0.9433 |
|
| 77 |
+
| 0.0014 | 6.0 | 10482 | 0.3780 | 0.9416 | 0.9417 |
|
| 78 |
+
| 0.1803 | 7.0 | 12229 | 0.3196 | 0.9519 | 0.9519 |
|
| 79 |
+
| 0.0004 | 8.0 | 13976 | 0.2672 | 0.9651 | 0.9651 |
|
| 80 |
+
|
| 81 |
+
|
| 82 |
+
### Framework versions
|
| 83 |
+
|
| 84 |
+
- Transformers 4.52.4
|
| 85 |
+
- Pytorch 2.7.1+cu126
|
| 86 |
+
- Datasets 3.6.0
|
| 87 |
+
- Tokenizers 0.21.1
|