Audio Classification
Transformers
Safetensors
audio-spectrogram-transformer
Generated from Trainer
Eval Results (legacy)
Instructions to use Vladimirlv/ast-finetuned-audioset-10-10-0.4593-heart-sounds with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Vladimirlv/ast-finetuned-audioset-10-10-0.4593-heart-sounds with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("audio-classification", model="Vladimirlv/ast-finetuned-audioset-10-10-0.4593-heart-sounds")# Load model directly from transformers import AutoFeatureExtractor, AutoModelForAudioClassification extractor = AutoFeatureExtractor.from_pretrained("Vladimirlv/ast-finetuned-audioset-10-10-0.4593-heart-sounds") model = AutoModelForAudioClassification.from_pretrained("Vladimirlv/ast-finetuned-audioset-10-10-0.4593-heart-sounds") - Notebooks
- Google Colab
- Kaggle
Model save
Browse files
README.md
CHANGED
|
@@ -1,39 +1,22 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
|
|
|
|
|
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
-
datasets:
|
| 6 |
-
- audiofolder
|
| 7 |
-
metrics:
|
| 8 |
-
- accuracy
|
| 9 |
model-index:
|
| 10 |
- name: ast-finetuned-audioset-10-10-0.4593-heart-sounds
|
| 11 |
-
results:
|
| 12 |
-
- task:
|
| 13 |
-
name: Audio Classification
|
| 14 |
-
type: audio-classification
|
| 15 |
-
dataset:
|
| 16 |
-
name: audiofolder
|
| 17 |
-
type: audiofolder
|
| 18 |
-
config: default
|
| 19 |
-
split: validation
|
| 20 |
-
args: default
|
| 21 |
-
metrics:
|
| 22 |
-
- name: Accuracy
|
| 23 |
-
type: accuracy
|
| 24 |
-
value: 0.9679878048780488
|
| 25 |
---
|
| 26 |
|
| 27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 28 |
should probably proofread and complete it, then remove this comment. -->
|
| 29 |
|
| 30 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/vldmrl-org/HeartDiseaseDetector/runs/
|
|
|
|
| 31 |
# ast-finetuned-audioset-10-10-0.4593-heart-sounds
|
| 32 |
|
| 33 |
-
This model
|
| 34 |
-
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 0.1359
|
| 36 |
-
- Accuracy: 0.9680
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
@@ -63,20 +46,6 @@ The following hyperparameters were used during training:
|
|
| 63 |
- lr_scheduler_warmup_ratio: 0.1
|
| 64 |
- num_epochs: 8
|
| 65 |
|
| 66 |
-
### Training results
|
| 67 |
-
|
| 68 |
-
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|
| 69 |
-
|:-------------:|:------:|:----:|:--------:|:---------------:|
|
| 70 |
-
| 0.2137 | 1.0 | 83 | 0.9329 | 0.1661 |
|
| 71 |
-
| 0.1561 | 2.0 | 166 | 0.8841 | 0.2494 |
|
| 72 |
-
| 0.1113 | 3.0 | 249 | 0.9588 | 0.1119 |
|
| 73 |
-
| 0.0478 | 4.0 | 332 | 0.9588 | 0.1134 |
|
| 74 |
-
| 0.025 | 4.9483 | 410 | 0.9649 | 0.1086 |
|
| 75 |
-
| 0.0338 | 6.0 | 493 | 0.1260 | 0.9634 |
|
| 76 |
-
| 0.0179 | 7.0 | 576 | 0.1392 | 0.9680 |
|
| 77 |
-
| 0.012 | 7.9726 | 656 | 0.1359 | 0.9680 |
|
| 78 |
-
|
| 79 |
-
|
| 80 |
### Framework versions
|
| 81 |
|
| 82 |
- Transformers 4.49.0
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
+
license: bsd-3-clause
|
| 4 |
+
base_model: MIT/ast-finetuned-audioset-10-10-0.4593
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
model-index:
|
| 8 |
- name: ast-finetuned-audioset-10-10-0.4593-heart-sounds
|
| 9 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
|
| 15 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/vldmrl-org/HeartDiseaseDetector/runs/n9fzp3eh)
|
| 16 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/vldmrl-org/HeartDiseaseDetector/runs/n9fzp3eh)
|
| 17 |
# ast-finetuned-audioset-10-10-0.4593-heart-sounds
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [MIT/ast-finetuned-audioset-10-10-0.4593](https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.4593) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 46 |
- lr_scheduler_warmup_ratio: 0.1
|
| 47 |
- num_epochs: 8
|
| 48 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
### Framework versions
|
| 50 |
|
| 51 |
- Transformers 4.49.0
|