# From PyPI
pip install audiocraft

# From GitHub (latest)
pip install git+https://github.com/facebookresearch/audiocraft.git

# Or use HuggingFace Transformers
pip install transformers torch torchaudio

from audiocraft.models import MusicGen

# Load model
model = MusicGen.get_pretrained('facebook/musicgen-small')

# Set generation parameters
model.set_generation_params(
    duration=8,  # seconds
    top_k=250,
    temperature=1.0
)

# Generate from text
descriptions = ["happy upbeat electronic dance music with synths"]
wav = model.generate(descriptions)

# Save audio
torchaudio.save("output.wav", wav[0].cpu(), sample_rate=32000)

from transformers import AutoProcessor, MusicgenForConditionalGeneration

# Load model and processor
processor = AutoProcessor.from_pretrained("facebook/musicgen-small")
model = MusicgenForConditionalGeneration.from_pretrained("facebook/musicgen-small")
model.to("cuda")

# Generate music
inputs = processor(
    text=["80s pop track with bassy drums and synth"],
    padding=True,
    return_tensors="pt"
).to("cuda")

audio_values = model.generate(
    **inputs,
    do_sample=True,
    guidance_scale=3,
    max_new_tokens=256
)

# Save
sampling_rate = model.config.audio_encoder.sampling_rate
scipy.io.wavfile.write("output.wav", rate=sampling_rate, data=audio_values[0, 0].cpu().numpy())

from audiocraft.models import AudioGen

# Load AudioGen
model = AudioGen.get_pretrained('facebook/audiogen-medium')

model.set_generation_params(duration=5)

# Generate sound effects
descriptions = ["dog barking in a park with birds chirping"]
wav = model.generate(descriptions)

torchaudio.save("sound.wav", wav[0].cpu(), sample_rate=16000)

AudioCraft Architecture:
┌──────────────────────────────────────────────────────────────┐
│                    Text Encoder (T5)                          │
│                         │                                     │
│                    Text Embeddings                            │
└────────────────────────┬─────────────────────────────────────┘
                         │
┌────────────────────────▼─────────────────────────────────────┐
│              Transformer Decoder (LM)                         │
│     Auto-regressively generates audio tokens                  │
│     Using efficient token interleaving patterns               │
└────────────────────────┬─────────────────────────────────────┘
                         │
┌────────────────────────▼─────────────────────────────────────┐
│                EnCodec Audio Decoder                          │
│        Converts tokens back to audio waveform                 │
└──────────────────────────────────────────────────────────────┘

from audiocraft.models import MusicGen

model = MusicGen.get_pretrained('facebook/musicgen-medium')

# Configure generation
model.set_generation_params(
    duration=30,          # Up to 30 seconds
    top_k=250,            # Sampling diversity
    top_p=0.0,            # 0 = use top_k only
    temperature=1.0,      # Creativity (higher = more varied)
    cfg_coef=3.0          # Text adherence (higher = stricter)
)

# Generate multiple samples
descriptions = [
    "epic orchestral soundtrack with strings and brass",
    "chill lo-fi hip hop beat with jazzy piano",
    "energetic rock song with electric guitar"
]

# Generate (returns [batch, channels, samples])
wav = model.generate(descriptions)

# Save each
for i, audio in enumerate(wav):
    torchaudio.save(f"music_{i}.wav", audio.cpu(), sample_rate=32000)

from audiocraft.models import MusicGen

# Load melody model
model = MusicGen.get_pretrained('facebook/musicgen-melody')
model.set_generation_params(duration=30)

# Load melody audio
melody, sr = torchaudio.load("melody.wav")

# Generate with melody conditioning
descriptions = ["acoustic guitar folk song"]
wav = model.generate_with_chroma(descriptions, melody, sr)

torchaudio.save("melody_conditioned.wav", wav[0].cpu(), sample_rate=32000)

from audiocraft.models import MusicGen

# Load stereo model
model = MusicGen.get_pretrained('facebook/musicgen-stereo-medium')
model.set_generation_params(duration=15)

descriptions = ["ambient electronic music with wide stereo panning"]
wav = model.generate(descriptions)

# wav shape: [batch, 2, samples] for stereo
print(f"Stereo shape: {wav.shape}")  # [1, 2, 480000]
torchaudio.save("stereo.wav", wav[0].cpu(), sample_rate=32000)

from transformers import AutoProcessor, MusicgenForConditionalGeneration

processor = AutoProcessor.from_pretrained("facebook/musicgen-medium")
model = MusicgenForConditionalGeneration.from_pretrained("facebook/musicgen-medium")

# Load audio to continue

audio, sr = torchaudio.load("intro.wav")

# Process with text and audio
inputs = processor(
    audio=audio.squeeze().numpy(),
    sampling_rate=sr,
    text=["continue with a epic chorus"],
    padding=True,
    return_tensors="pt"
)

# Generate continuation
audio_values = model.generate(**inputs, do_sample=True, guidance_scale=3, max_new_tokens=512)

from audiocraft.models import MusicGen

# Load style model
model = MusicGen.get_pretrained('facebook/musicgen-style')

# Configure generation with style
model.set_generation_params(
    duration=30,
    cfg_coef=3.0,
    cfg_coef_beta=5.0  # Style influence
)

# Configure style conditioner
model.set_style_conditioner_params(
    eval_q=3,          # RVQ quantizers (1-6)
    excerpt_length=3.0  # Style excerpt length
)

# Load style reference
style_audio, sr = torchaudio.load("reference_style.wav")

# Generate with text + style
descriptions = ["upbeat dance track"]
wav = model.generate_with_style(descriptions, style_audio, sr)

# Generate matching style without text prompt
model.set_generation_params(
    duration=30,
    cfg_coef=3.0,
    cfg_coef_beta=None  # Disable double CFG for style-only
)

wav = model.generate_with_style([None], style_audio, sr)

from audiocraft.models import AudioGen

model = AudioGen.get_pretrained('facebook/audiogen-medium')
model.set_generation_params(duration=10)

# Generate various sounds
descriptions = [
    "thunderstorm with heavy rain and lightning",
    "busy city traffic with car horns",
    "ocean waves crashing on rocks",
    "crackling campfire in forest"
]

wav = model.generate(descriptions)

for i, audio in enumerate(wav):
    torchaudio.save(f"sound_{i}.wav", audio.cpu(), sample_rate=16000)

from audiocraft.models import CompressionModel

# Load EnCodec
model = CompressionModel.get_pretrained('facebook/encodec_32khz')

# Load audio
wav, sr = torchaudio.load("audio.wav")

# Ensure correct sample rate
if sr != 32000:
    resampler = torchaudio.transforms.Resample(sr, 32000)
    wav = resampler(wav)

# Encode to tokens
with torch.no_grad():
    encoded = model.encode(wav.unsqueeze(0))
    codes = encoded[0]  # Audio codes

# Decode back to audio
with torch.no_grad():
    decoded = model.decode(codes)

torchaudio.save("reconstructed.wav", decoded[0].cpu(), sample_rate=32000)

from audiocraft.models import MusicGen

class MusicGenerator:
    def __init__(self, model_name="facebook/musicgen-medium"):
        self.model = MusicGen.get_pretrained(model_name)
        self.sample_rate = 32000

    def generate(self, prompt, duration=30, temperature=1.0, cfg=3.0):
        self.model.set_generation_params(
            duration=duration,
            top_k=250,
            temperature=temperature,
            cfg_coef=cfg
        )

        with torch.no_grad():
            wav = self.model.generate([prompt])

        return wav[0].cpu()

    def generate_batch(self, prompts, duration=30):
        self.model.set_generation_params(duration=duration)

        with torch.no_grad():
            wav = self.model.generate(prompts)

        return wav.cpu()

    def save(self, audio, path):
        torchaudio.save(path, audio, sample_rate=self.sample_rate)

# Usage
generator = MusicGenerator()
audio = generator.generate(
    "epic cinematic orchestral music",
    duration=30,
    temperature=1.0
)
generator.save(audio, "epic_music.wav")

from pathlib import Path
from audiocraft.models import AudioGen

def batch_generate_sounds(sound_specs, output_dir):
    """
    Generate multiple sounds from specifications.

    Args:
        sound_specs: list of {"name": str, "description": str, "duration": float}
        output_dir: output directory path
    """
    model = AudioGen.get_pretrained('facebook/audiogen-medium')
    output_dir = Path(output_dir)
    output_dir.mkdir(exist_ok=True)

    results = []

    for spec in sound_specs:
        model.set_generation_params(duration=spec.get("duration", 5))

        wav = model.generate([spec["description"]])

        output_path = output_dir / f"{spec['name']}.wav"
        torchaudio.save(str(output_path), wav[0].cpu(), sample_rate=16000)

        results.append({
            "name": spec["name"],
            "path": str(output_path),
            "description": spec["description"]
        })

    return results

# Usage
sounds = [
    {"name": "explosion", "description": "massive explosion with debris", "duration": 3},
    {"name": "footsteps", "description": "footsteps on wooden floor", "duration": 5},
    {"name": "door", "description": "wooden door creaking and closing", "duration": 2}
]

results = batch_generate_sounds(sounds, "sound_effects/")

from audiocraft.models import MusicGen

model = MusicGen.get_pretrained('facebook/musicgen-small')

def generate_music(prompt, duration, temperature, cfg_coef):
    model.set_generation_params(
        duration=duration,
        temperature=temperature,
        cfg_coef=cfg_coef
    )

    with torch.no_grad():
        wav = model.generate([prompt])

    # Save to temp file
    path = "temp_output.wav"
    torchaudio.save(path, wav[0].cpu(), sample_rate=32000)
    return path

demo = gr.Interface(
    fn=generate_music,
    inputs=[
        gr.Textbox(label="Music Description", placeholder="upbeat electronic dance music"),
        gr.Slider(1, 30, value=8, label="Duration (seconds)"),
        gr.Slider(0.5, 2.0, value=1.0, label="Temperature"),
        gr.Slider(1.0, 10.0, value=3.0, label="CFG Coefficient")
    ],
    outputs=gr.Audio(label="Generated Music"),
    title="MusicGen Demo"
)

demo.launch()

# Use smaller model
model = MusicGen.get_pretrained('facebook/musicgen-small')

# Clear cache between generations
torch.cuda.empty_cache()

# Generate shorter durations
model.set_generation_params(duration=10)  # Instead of 30

# Use half precision
model = model.half()

# Process multiple prompts at once (more efficient)
descriptions = ["prompt1", "prompt2", "prompt3", "prompt4"]
wav = model.generate(descriptions)  # Single batch

# Instead of
for desc in descriptions:
    wav = model.generate([desc])  # Multiple batches (slower)