---
license: mit
language:
- en
base_model:
- facebook/wav2vec2-base
pipeline_tag: audio-classification
tags:
- audio-classification
- biology
- birds
- conservation
datasets:
- greenarcade/wav2vec2-vd-bird-sound-classification-dataset
library_name: transformers
model-index:
  - name: wav2vec2-vd-bird-sound-classification
    results:
      - task:
          type: image-classification
        dataset:
          name: Custom Bird Dataset
          type: image-classification
        metrics:
          - name: Accuracy
            type: accuracy
            value: 91.11
          - name: F1 Score
            type: f1
            value: 89.41
          - name: Inference Speed (sec)
            type: inference_time
            value: 0.476
          - name: Error Rate
            type: error_rate
            value: 8.89
          - name: Average ROC AUC
            type: roc_auc
            value: 98.20
          - name: Average Precision
            type: avg_precision
            value: 93.63
        source:
          name: Custom Evaluation
          url: https://huggingface.co/greeenboi/wav2vec2-vd-bird-sound-classification
---

# greenarcade/wav2vec2-vd-bird-sound-classification

Bird sound classification model trained on my custom dataset. Identifies local bird species from audio recordings.

## Usage

```python
from transformers import pipeline

classifier = pipeline("audio-classification", "greenarcade/wav2vec2-vd-bird-sound-classification")
result = classifier("your_audio.wav", top_k=3)
```

***

- **Developed by:** [Suvan GS](https://github.com/greeenboi) & [Dharanya T]
- **Model type:** Transformers
- **License:** MIT

### Model Sources [optional]

<!-- Provide the basic links for the model. -->

- **Repository:** [Minor Project](https://github.com/greeenboi/minor-project)
- **Paper :** Coming Soon
- **Demo [optional]:** [Space](https://huggingface.co/spaces/greenarcade/wav2vec2-vd-bird-sound-classification-space)

## Uses

Used to Classify the sounds for the 21 species of birds observed at Vedanthangal Bird Sanctuary


### Out-of-Scope Use

The model will not work for any of the species not listed below:

|Species Common Name|
|-----|
|Asian openbill stork|
|Blue-tailed bee-eater|
|Common kingfisher|
|Eurasian spoonbill|
|Fulvous whistling duck|
|Garganey|
|Glossy ibis|
|Golden oriole|
|Great egret|
|Grey Heron|
|Indian pond heron|
|Indian spot-billed duck|
|Little egret|
|Northern pintail|
|Northern shoveler|
|Painted stork|
|Rosy starling|
|Spot-billed pelican|
|Spotted owlet|
|White Ibis|
|White-throated kingfisher|


***

## Training Details

### Training Data

<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

[More Information Needed]

### Training Procedure

<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->

#### Preprocessing [optional]

[More Information Needed]


#### Training Hyperparameters

- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->

#### Speeds, Sizes, Times [optional]

<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->

[More Information Needed]

## Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->

### Testing Data, Factors & Metrics

#### Testing Data

<!-- This should link to a Dataset Card if possible. -->

[More Information Needed]

#### Factors

<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->

[More Information Needed]

#### Metrics

<!-- These are the evaluation metrics being used, ideally with a description of why. -->

[More Information Needed]

### Results

[More Information Needed]

#### Summary



## Environmental Impact

<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->

Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).

- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]

## Technical Specifications [optional]

### Model Architecture and Objective

[More Information Needed]

### Compute Infrastructure

[More Information Needed]

#### Hardware

[More Information Needed]

#### Software

[More Information Needed]

## Citation [optional]

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

**BibTeX:**

[More Information Needed]

**APA:**

[More Information Needed]

## Glossary [optional]

<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->

[More Information Needed]

## More Information [optional]

[More Information Needed]

## Model Card Authors [optional]

[More Information Needed]

## Model Card Contact

[More Information Needed]