AudioGen - Implemented Audio Generation [DRAFT PR]

.github/workflows/labgraph_audiogen.yml

@@ -0,0 +1,31 @@
+name: AudioGen Tests
+
+on: [push]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v2
+
+    - name: Setup Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.8'
+
+    - name: Install dependencies
+      run: |
+        cd extensions/lg_audiogen 
+        python -m pip install --upgrade pip
+        sudo apt-get install ffmpeg
+        pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
+        pip install --pre xformers
+        pip install -e .
+        pip install pytest
+
+    - name: Run tests
+      run: |
+        cd extensions/lg_audiogen
+        pytest -vvv

extensions/lg_audiogen/README.md

@@ -0,0 +1,68 @@
+# Audiogen
+
+Audiogen is a Python command-line tool that uses models from Audiocraft's AudioGen to generate audio from specified descriptions. This tool can generate a single piece of audio based on a specific description or multiple pieces of audio based on a batch file containing multiple descriptions.
+
+## Features
+
+* Ability to specify duration of the generated audio.
+* Ability to generate audio based on a batch file.
+* Ability to specify the model to be used for the audio generation.
+* Ability to set the output file name.
+
+## Setup
+
+Audiocraft needs Python 3.8 or higher to run. If you have a suitable version of Python installed, you can install Audiogen with pip:
+
+```shell
+pip install -e .
+```
+
+## Usage
+
+### Command-line interface
+
+The CLI usage for Audiogen is `lg_audiogen [OPTIONS] [DESCRIPTION]...`.
+
+### Options
+
+* `description`: the description based on which the audio is to be generated.
+* `duration, -d`: duration of the generated audio, default is 5.
+* `model, -m`: name of the Audiocraft AudioGen model to use, default is 'facebook/audiogen-medium'.
+* `output, -o`: name of the output file.
+* `batch`: file name for batch audio description.
+
+### Example
+
+To generate an audio file you would use the following command:
+
+```shell
+lg_audiogen -d 5 -m 'facebook/audiogen-medium' -o 'my_output' 'dog barking'
+
+lg_audiogen 'dog barking'
+
+lg_audiogen -b 'batch.txt'
+```
+
+### Batch File Format
+
+The batch file should contain one description per line. The descriptions should be in the same format as the descriptions used in the command-line interface.
+
+Example:
+
+*batch.txt*
+```txt
+Natural sounds of a rainforest
+Bird Chirping in the background 
+```
+
+### Samples
+
+[Google Drive Folder](https://drive.google.com/drive/folders/1kdWB1CBog4NGVJ7jWddKLtBAuPm3gwDq?usp=drive_link)
+
+## O.S Support
+
+```Tested on Ubuntu 22.04 (Jammy) LTS```
+
+## Error Handling
+
+If the batch file is not found, a notable error message will be presented. Moreover, if a description is not provided when not using a batch file, a misusage error will be raised.

extensions/lg_audiogen/lg_audiogen/main.py

@@ -0,0 +1,55 @@
+import click
+import torch
+from audiocraft.models import AudioGen
+from audiocraft.data.audio import audio_write
+
+DEFAULT_AUDIOGEN_MODEL = 'facebook/audiogen-medium'
+DEFAULT_AUDIO_DURATION = 5
+
+@click.command()
+@click.argument('description', nargs=-1, required=False)
+@click.option('--duration', '-d', default=DEFAULT_AUDIO_DURATION, help='Duration of the generated audio.')
+@click.option('--model', '-m', default=DEFAULT_AUDIOGEN_MODEL, help='Name of the Audiocraft AudioGen model to use.')
+@click.option('--output', '-o', help='Name of the output file.')
+@click.option('--batch', '-b', type=click.Path(), help='File name for batch audio description.')
+def parse_arguments(description, duration, model, output, batch):
+    """
+    Generates audio from description using Audiocraft's AudioGen.
+    """
+    if batch:
+        try:
+            with open(batch, mode='r', encoding='utf-8') as f:
+                descriptions = [line.strip() for line in f.readlines()]
+        except FileNotFoundError:
+            print(f"File {batch} not found. Please check the file path and try again.")
+    else:
+        if not description:
+            raise click.BadParameter("Description argument is required when not using --batch.")
+        descriptions = [' '.join(description)]
+    run_audio_generation(descriptions, duration, model, output)
+
+def run_audio_generation(descriptions, duration, model_name, output):
+    """
+    Load Audiocraft's AudioGen model and generate audio from the description.
+
+    @param descriptions: The parsed arguments.
+    @param duration: Duration of the generated audio.
+    @param model_name: Name of the Audiocraft AudioGen model to use.
+    @param output: Name of the output file.
+    """
+    print(f"Running lg_audiogen with descriptions: {descriptions}")
+
+    # Load Audiocraft's AudioGen model and set generation params.
+    model = AudioGen.get_pretrained(model_name)
+    model.set_generation_params(duration=duration)
+
+    # Generate audio from the descriptions
+    wav = model.generate(descriptions)
+    batch_output = output
+    # Save the generated audios.
+    for idx, one_wav in enumerate(wav):
+        # Will save under {output}{idx}.wav, with loudness normalization at -14 db LUFS.
+        if not output:
+            batch_output = descriptions[idx].replace(' ', '_')
+        audio_write(f'{batch_output}{idx}', one_wav.cpu(),
+                    model.sample_rate, strategy="loudness", loudness_compressor=True)

extensions/lg_audiogen/setup.py

@@ -0,0 +1,22 @@
+from setuptools import setup, find_packages
+
+setup(
+    name='lg_audiogen',
+    version='0.1',
+    description="A Command-line interface to use Audiocraft for labgraph",
+    long_description="""
+    A Command-line interface to facilitate the usage of Audiocraft's models
+    to generate and process audio on labgraph
+    """,
+    packages=find_packages(),
+    install_requires=[
+        "Click>=8.1.7",
+        "torch>=2.1.0",
+        "torchaudio>=2.1.0",
+        "audiocraft==1.1.0",
+    ],
+    entry_points='''
+        [console_scripts]
+        lg_audiogen=lg_audiogen.main:parse_arguments
+    ''',
+)

extensions/lg_audiogen/tests/test_main.py

@@ -0,0 +1,13 @@
+import os
+import subprocess
+
+def test_single_description():
+    '''
+        Tests output with a single description
+    '''
+    # Run the script with an example description
+    subprocess.run(["lg_audiogen", "dog barking"],
+                   capture_output=True, text=True, check=False)
+    # Assert that the output file was created
+    assert os.path.exists("dog_barking0.wav"), "Output file dog_barking0.wav was not created"
+    os.remove("dog_barking0.wav")