from transformers import AutoProcessor, MusicFlamingoForConditionalGeneration


model_id = "nvidia/music-flamingo-2601-hf"
processor = AutoProcessor.from_pretrained(model_id)
model = MusicFlamingoForConditionalGeneration.from_pretrained(model_id, device_map="auto")

conversation = [
    {
        "role": "user",
        "content": [
            {"type": "text", "text": "Describe this track in full detail - tell me the genre, tempo, and key, then dive into the instruments, production style, and overall mood it creates."},
            {"type": "audio", "path": "https://huggingface.co/datasets/nvidia/AudioSkills/resolve/main/assets/song_1.mp3"},
        ],
    }
]

inputs = processor.apply_chat_template(
    conversation,
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
).to(model.device)
inputs["input_features"] = inputs["input_features"].to(model.dtype)

outputs = model.generate(**inputs, max_new_tokens=500)

decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)
print(decoded_outputs)

from transformers import AutoProcessor, MusicFlamingoForConditionalGeneration


model_id = "nvidia/music-flamingo-2601-hf"
processor = AutoProcessor.from_pretrained(model_id)
model = MusicFlamingoForConditionalGeneration.from_pretrained(model_id, device_map="auto")

conversation = [
    {
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": "Write a rich caption that blends the technical details (genre, BPM, key, chords, mix) with how the song feels emotionally and dynamically as it unfolds.",
            },
            {"type": "audio", "path": "https://huggingface.co/datasets/nvidia/AudioSkills/resolve/main/assets/song_1.mp3"},
        ],
    },
    {
        "role": "assistant",
        "content": [{"type": "text", "text": "This energetic Eurodance anthem at 150 BPM in E major combines bright synth arpeggios with a punchy four-on-the-floor beat..."}],
    },
    {
        "role": "user",
        "content": [
            {"type": "text", "text": "What instruments stand out the most?"},
        ],
    },
]

inputs = processor.apply_chat_template(
    conversation,
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
).to(model.device)
inputs["input_features"] = inputs["input_features"].to(model.dtype)

outputs = model.generate(**inputs, max_new_tokens=500)

decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)
print(decoded_outputs)

from transformers import AutoProcessor, MusicFlamingoForConditionalGeneration


model_id = "nvidia/music-flamingo-2601-hf"
processor = AutoProcessor.from_pretrained(model_id)
model = MusicFlamingoForConditionalGeneration.from_pretrained(model_id, device_map="auto")

conversations = [
    [
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Describe this track in full detail - tell me the genre, tempo, and key, then dive into the instruments, production style, and overall mood it creates."},
                {
                    "type": "audio",
                    "path": "https://huggingface.co/datasets/nvidia/AudioSkills/resolve/main/assets/song_1.mp3",
                },
            ],
        }
    ],
    [
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "Generate a structured lyric sheet from the input music.",
                },
                {"type": "audio", "path": "https://huggingface.co/datasets/nvidia/AudioSkills/resolve/main/assets/song_2.mp3"},
            ],
        }
    ],
]

inputs = processor.apply_chat_template(
    conversations,
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
).to(model.device)
inputs["input_features"] = inputs["input_features"].to(model.dtype)

outputs = model.generate(**inputs, max_new_tokens=500)

decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)
print(decoded_outputs)

from transformers import AutoProcessor, MusicFlamingoForConditionalGeneration


model_id = "nvidia/music-flamingo-2601-hf"
processor = AutoProcessor.from_pretrained(model_id)
model = MusicFlamingoForConditionalGeneration.from_pretrained(model_id, device_map="auto")
model.train()

conversation = [
    [
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Break the track down like a critic - list its tempo, key, and chordal motion, then explain the textures, dynamics, and emotional impact of the performance."},
                {"type": "audio", "path": "https://huggingface.co/datasets/nvidia/AudioSkills/resolve/main/assets/song_1.mp3"},
            ],
        },
        {
            "role": "assistant",
            "content": [{"type": "text", "text": "This Eurodance track operates at 150 BPM in E major, with harmonic movement centering on the I-vi-IV-V family. The production features layered synth arpeggios, a four-on-the-floor kick pattern, and a mezzo-soprano lead vocal with bright timbre. Dynamically, the track builds through verses into an anthemic chorus with full synth orchestration and backing vocals, creating an uplifting, euphoric atmosphere characteristic of late 2000s dance-pop."}],
        }
    ],
    [
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "Describe this song from both a technical and artistic lens: mention tempo, harmony, and instrumentation, but also mood, lyrical themes, and structure.",
                },
                {"type": "audio", "path": "https://huggingface.co/datasets/nvidia/AudioSkills/resolve/main/assets/song_2.mp3"},
            ],
        },
        {
            "role": "assistant",
            "content": [{"type": "text", "text": "This electronic pop track combines upbeat production with playful lyrical themes centered around late-night pizza cravings. The structure follows a verse-chorus format with recurring melodic motifs and rhythmic patterns that emphasize the celebratory, lighthearted mood of the piece."}],
        }

    ]
]

inputs = processor.apply_chat_template(
    conversation,
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
    processor_kwargs={"output_labels": True},
).to(model.device)
inputs["input_features"] = inputs["input_features"].to(model.dtype)

loss = model(**inputs).loss
loss.backward()