pip install diffusers
pip install soundfile   # for saving audio

from transformers import AutoProcessor, AutoModelForTextToWaveform

model_id = "vibevoice/VibeVoice-1.5B-hf"  # "vibevoice/VibeVoice-7B-hf"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForTextToWaveform.from_pretrained(model_id)

import os
from transformers import AutoProcessor, AutoModelForTextToWaveform

model_id = "vibevoice/VibeVoice-1.5B-hf"   # "vibevoice/VibeVoice-7B-hf"
text = "Hello, nice to meet you. How are you?"

# Load model
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForTextToWaveform.from_pretrained(model_id, device_map="auto")

# Prepare input
conversation = [{"role": "0", "content": [{"type": "text", "text": text}]}]
inputs = processor.apply_chat_template(
    conversation, return_dict=True, tokenize=True, add_generation_prompt=True,
).to(model.device, model.dtype)

# Generate!
audio = model.generate(**inputs)

# Save to file
file_name = f"{os.path.basename(model_id)}_tts.wav"
processor.save_audio(audio, file_name)
print(f"Saved output to {file_name}")

import os
from transformers import AutoProcessor, AutoModelForTextToWaveform, set_seed

model_id = "vibevoice/VibeVoice-1.5B-hf"   # "vibevoice/VibeVoice-7B-hf"
text = "Hello, nice to meet you. How are you?"
set_seed(42)  # for deterministic results

# Load model
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForTextToWaveform.from_pretrained(model_id, device_map="auto")
sampling_rate = processor.feature_extractor.sampling_rate

# Prepare input
conversation = [
    {
        "role": "0",
        "content": [
            {"type": "text", "text": text},
            {
                "type": "audio",
                "url": "https://huggingface.co/datasets/bezzam/vibevoice_samples/resolve/main/voices/en-Alice_woman.wav",
            },
        ],
    }
]
inputs = processor.apply_chat_template(
    conversation, return_dict=True, tokenize=True, add_generation_prompt=True,
).to(model.device, model.dtype)

# Generate!
audio = model.generate(**inputs)

# Save to file
fn = f"{os.path.basename(model_id)}_tts_clone.wav"
processor.save_audio(audio, fn)
print(f"Saved output to {fn}")

import os
import time
from transformers import AutoProcessor, AutoModelForTextToWaveform

model_id = "vibevoice/VibeVoice-1.5B-hf"   # "vibevoice/VibeVoice-7B-hf"
max_new_tokens = 400  # `None` to ensure full generation

# create conversation with an audio for the first time a speaker appears to clone that particular voice
conversation = [
    {
        "role": "0",
        "content": [
            {
                "type": "text", "text": "Hello everyone, and welcome to the VibeVoice podcast. I'm your host, Linda, and today we're getting into one of the biggest debates in all of sports: who's the greatest basketball player of all time? I'm so excited to have Thomas here to talk about it with me.",
            },
            {
                "type": "audio", "url": "https://huggingface.co/datasets/bezzam/vibevoice_samples/resolve/main/voices/en-Alice_woman.wav",
            },
        ],
    },
    {
        "role": "1",
        "content": [
            {
                "type": "text", "text": "Thanks so much for having me, Linda. You're absolutely right—this question always brings out some seriously strong feelings.",
            },
            {
                "type": "audio", "url": "https://huggingface.co/datasets/bezzam/vibevoice_samples/resolve/main/voices/en-Frank_man.wav",
            },
        ],
    },
    {
        "role": "0",
        "content": [
            {
                "type": "text", "text": "Okay, so let's get right into it. For me, it has to be Michael Jordan. Six trips to the Finals, six championships. That kind of perfection is just incredible.",
            },
        ],
    },
    {
        "role": "1",
        "content": [
            {
                "type": "text", "text": "Oh man, the first thing that always pops into my head is that shot against the Cleveland Cavaliers back in '89. Jordan just rises, hangs in the air forever, and just sinks it",
            },
        ],
    },
]

# Load model
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForTextToWaveform.from_pretrained(model_id, device_map="auto")

# prepare inputs
inputs = processor.apply_chat_template(
    conversation, return_dict=True, tokenize=True, add_generation_prompt=True,
).to(model.device, model.dtype)

# Generate audio with a progress bar to track generation
model.generation_config.max_new_tokens = max_new_tokens
start_time = time.time()
audio = model.generate(**inputs, monitor_progress=True)
generation_time = time.time() - start_time
print(f"Generation time: {generation_time:.2f} seconds")

# Save audio
fn = f"{os.path.basename(model_id)}_script.wav"
processor.save_audio(audio, fn)
print(f"Saved output to {fn}")

import os
import time
from transformers import AutoProcessor, AutoModelForTextToWaveform

model_id = "vibevoice/VibeVoice-1.5B-hf"   # "vibevoice/VibeVoice-7B-hf"
max_new_tokens = 400  # `None` to ensure full generation

conversation = [
    [
        {
            "role": "0",
            "content": [
                {
                    "type": "text", "text": "Hello everyone, and welcome to the VibeVoice podcast. I'm your host, Linda, and today we're getting into one of the biggest debates in all of sports: who's the greatest basketball player of all time? I'm so excited to have Thomas here to talk about it with me.",
                },
                {
                    "type": "audio",
                    "url": "https://huggingface.co/datasets/bezzam/vibevoice_samples/resolve/main/voices/en-Alice_woman.wav",
                },
            ],
        },
        {
            "role": "1",
            "content": [
                {
                    "type": "text", "text": "Thanks so much for having me, Linda.",
                },
                {
                    "type": "audio", "url": "https://huggingface.co/datasets/bezzam/vibevoice_samples/resolve/main/voices/en-Frank_man.wav",
                },
            ],
        },
    ],
    [
        {
            "role": "0",
            "content": [
                {
                    "type": "text", "text": "Hello and welcome to Planet in Peril. I'm your host, Alice. We're here today to discuss a really sobering new report that looks back at the last ten years of climate change. I'm joined by our expert panel. Welcome Carter, Frank, and Maya.",
                },
                {
                    "type": "audio", "url": "https://huggingface.co/datasets/bezzam/vibevoice_samples/resolve/main/voices/en-Alice_woman.wav",
                },
            ],
        },
        {
            "role": "1",
            "content": [
                {"type": "text", "text": "Hi Alice, it's great to be here. I'm Carter."},
                {
                    "type": "audio", "url": "https://huggingface.co/datasets/bezzam/vibevoice_samples/resolve/main/voices/en-Carter_man.wav",
                },
            ],
        },
        {
            "role": "2",
            "content": [
                {"type": "text", "text": "Hello, uh, I'm Frank. Good to be on."},
                {
                    "type": "audio", "url": "https://huggingface.co/datasets/bezzam/vibevoice_samples/resolve/main/voices/en-Frank_man.wav",
                },
            ],
        },
        {
            "role": "3",
            "content": [
                {"type": "text", "text": "And I'm Maya. Thanks for having me."},
                {
                    "type": "audio", "url": "https://huggingface.co/datasets/bezzam/vibevoice_samples/resolve/main/voices/en-Maya_woman.wav",
                },
            ],
        },
    ],
]

# Load model
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForTextToWaveform.from_pretrained(model_id, device_map="auto")

# prepare inputs
inputs = processor.apply_chat_template(
    conversation, return_dict=True, tokenize=True, add_generation_prompt=True,
).to(model.device, model.dtype)

# Generate audio with a progress bar to track generation
model.generation_config.max_new_tokens = max_new_tokens
start_time = time.time()
audio = model.generate(**inputs, monitor_progress=True)
generation_time = time.time() - start_time
print(f"Generation time: {generation_time:.2f} seconds")

# Save audio
output_dir = f"{os.path.basename(model_id)}_batch"
processor.save_audio(audio, output_dir)
print(f"Saved output to {output_dir}")

import os
import soundfile as sf
from transformers import pipeline

model_id = "vibevoice/VibeVoice-1.5B-hf"   # "vibevoice/VibeVoice-7B-hf"
text = "Hello, nice to meet you. How are you?"
pipe = pipeline("text-to-speech", model=model_id)

# Generate!
conversation = [
    {
        "role": "0",
        "content": [
            {"type": "text", "text": text},
            {
                "type": "audio", "url": "https://huggingface.co/datasets/bezzam/vibevoice_samples/resolve/main/voices/en-Alice_woman.wav",
            },
        ],
    }
]
# optional kwargs for generation
generate_kwargs = {"guidance_scale": 1.3, "num_diffusion_steps": 10}
output = pipe(conversation, generate_kwargs=generate_kwargs)

# Save to file
fn = f"{os.path.basename(model_id)}_pipeline.wav"
sf.write(fn, output["audio"], output["sampling_rate"])
print(f"Saved output to {fn}")

from transformers import AutoProcessor, AutoModelForTextToWaveform


model_id = "vibevoice/VibeVoice-1.5B-hf"   # "vibevoice/VibeVoice-7B-hf"

# Load model and processor
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForTextToWaveform.from_pretrained(
    model_id,
    diffusion_loss_weight=0.75,  # by default, equal weighting (0.5) of language modeling loss (CE) and diffusion loss is applied
    device_map="auto"
)
model.train()

# Prepare batch of 2
conversation = [
    [
        {
            "role": "0",
            "content": [
                {
                    "type": "text", "text": "VibeVoice is this novel framework designed for generating expressive, long-form, multi-speaker, conversational audio.",
                },
                {
                    "type": "audio", "url": "https://huggingface.co/datasets/bezzam/vibevoice_samples/resolve/main/realtime_model/vibevoice_tts_german.wav",
                },
            ],
        }
    ],
    # NOTE: multiple speakers not supported yet
    [
        {
            "role": "0",
            "content": [
                {
                    "type": "text", "text": "Hello everyone and welcome to the VibeVoice podcast. I'm your host, Alex, and today we're getting into one of the biggest debates in all of sports: who's the greatest basketball player of all time? I'm so excited to have Sam here to talk about it with me. Thanks so much for having me, Alex. And you're absolutely right. This question always brings out some seriously strong feelings. Okay, so let's get right into it. For me, it has to be Michael Jordan. Six trips to the finals, six championships. That kind of perfection is just incredible. Oh man, the first thing that always pops into my head is that shot against the Cleveland Cavaliers back in '89. Jordan just rises, hangs in the air forever, and just sinks it.",
                },
                {
                    "type": "audio",
                    "url": "https://huggingface.co/datasets/bezzam/vibevoice_samples/resolve/main/example_output/VibeVoice-1.5B_output.wav",
                },
            ],
        }
    ],
]

# Process with apply_chat_template and output_labels=True for training
inputs = processor.apply_chat_template(
    conversation,
    tokenize=True,
    return_dict=True,
    processor_kwargs={"output_labels": True},
).to(model.device, model.dtype)

# Forward pass
outputs = model(**inputs, ddpm_batch_multiplier=2, num_diffusion_steps=2)
print(f"Total loss: {outputs.loss.item():.4f}")

# Backward pass
outputs.loss.backward()

import os
import time
import torch
from transformers import AutoModelForTextToWaveform, AutoProcessor, CompileConfig


model_id = "vibevoice/VibeVoice-1.5B-hf"   # "vibevoice/VibeVoice-7B-hf"
num_warmup = 5
max_new_tokens = 128

torch.set_float32_matmul_precision("high")

# Load processor + model
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForTextToWaveform.from_pretrained(model_id, dtype=torch.bfloat16, device_map="auto").eval()

# Prepare inputs
conversation = [
    [
        {
            "role": "0",
            "content": [
                {"type": "text", "text": "VibeVoice is a novel framework for generating expressive audio."},
                {
                    "type": "audio", "url": "https://huggingface.co/datasets/bezzam/vibevoice_samples/resolve/main/realtime_model/vibevoice_tts_german.wav",
                },
            ],
        }
    ],
] * 4  # batch size 4
inputs = processor.apply_chat_template(
    conversation, tokenize=True, return_dict=True, add_generation_prompt=True,
).to(model.device, model.dtype)

compile_config = CompileConfig(mode="default", dynamic=False)

generate_kwargs = dict(
    **inputs,
    max_new_tokens=max_new_tokens,
    cache_implementation="static",
    compile_config=compile_config,
)

# Warmup
print("Warming up...")
warmup_start = time.time()
with torch.inference_mode():
    for _ in range(num_warmup):
        torch.compiler.cudagraph_mark_step_begin()
        _ = model.generate(**generate_kwargs)
torch.cuda.synchronize()
print(f"Warmup complete in {time.time() - warmup_start:.2f}s. Ready!")

# Apply model
with torch.inference_mode():
    torch.compiler.cudagraph_mark_step_begin()
    audio = model.generate(**generate_kwargs)
output_folder = f"{os.path.basename(model_id)}_compiled_output"
processor.save_audio(audio, output_folder)
print(f"Saved output to {output_folder}")