VibeVoice-ASR-HF

pip install "transformers>=5.3.0"

from transformers import AutoProcessor, VibeVoiceAsrForConditionalGeneration

model_id = "microsoft/VibeVoice-ASR-HF"
processor = AutoProcessor.from_pretrained(model_id)
model = VibeVoiceAsrForConditionalGeneration.from_pretrained(model_id)

from transformers import AutoProcessor, VibeVoiceAsrForConditionalGeneration

model_id = "microsoft/VibeVoice-ASR-HF"
processor = AutoProcessor.from_pretrained(model_id)
model = VibeVoiceAsrForConditionalGeneration.from_pretrained(model_id, device_map="auto")
print(f"Model loaded on {model.device} with dtype {model.dtype}")

# Prepare inputs using `apply_transcription_request`
inputs = processor.apply_transcription_request(
    audio="https://huggingface.co/datasets/bezzam/vibevoice_samples/resolve/main/example_output/VibeVoice-1.5B_output.wav",
).to(model.device, model.dtype)

# Apply model
output_ids = model.generate(**inputs)
generated_ids = output_ids[:, inputs["input_ids"].shape[1] :]
transcription = processor.decode(generated_ids)[0]
print("\n" + "=" * 60)
print("RAW OUTPUT")
print("=" * 60)
print(transcription)

transcription = processor.decode(generated_ids, return_format="parsed")[0]
print("\n" + "=" * 60)
print("TRANSCRIPTION (list of dicts)")
print("=" * 60)
for speaker_transcription in transcription:
    print(speaker_transcription)

# Remove speaker labels, only get raw transcription
transcription = processor.decode(generated_ids, return_format="transcription_only")[0]
print("\n" + "=" * 60)
print("TRANSCRIPTION ONLY")
print("=" * 60)
print(transcription)

"""
============================================================
RAW OUTPUT
============================================================
<|im_start|>assistant
[{"Start":0,"End":15.43,"Speaker":0,"Content":"Hello everyone and welcome to the Vibe Voice 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."},{"Start":15.43,"End":21.05,"Speaker":1,"Content":"Thanks so much for having me, Alex. And you're absolutely right. This question always brings out some seriously strong feelings."},{"Start":21.05,"End":31.66,"Speaker":0,"Content":"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."},{"Start":31.66,"End":40.93,"Speaker":1,"Content":"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."}]<|im_end|>
<|endoftext|>

============================================================
TRANSCRIPTION (list of dicts)
============================================================
{'Start': 0, 'End': 15.43, 'Speaker': 0, 'Content': "Hello everyone and welcome to the Vibe Voice 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."}
{'Start': 15.43, 'End': 21.05, 'Speaker': 1, 'Content': "Thanks so much for having me, Alex. And you're absolutely right. This question always brings out some seriously strong feelings."}
{'Start': 21.05, 'End': 31.66, 'Speaker': 0, 'Content': "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."}
{'Start': 31.66, 'End': 40.93, 'Speaker': 1, 'Content': "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."}

============================================================
TRANSCRIPTION ONLY
============================================================
Hello everyone and welcome to the Vibe Voice 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.
"""

from transformers import AutoProcessor, VibeVoiceAsrForConditionalGeneration

model_id = "microsoft/VibeVoice-ASR-HF"
processor = AutoProcessor.from_pretrained(model_id)
model = VibeVoiceAsrForConditionalGeneration.from_pretrained(model_id, device_map="auto")
print(f"Model loaded on {model.device} with dtype {model.dtype}")

# Without context
inputs = processor.apply_transcription_request(
    audio="https://huggingface.co/datasets/bezzam/vibevoice_samples/resolve/main/realtime_model/vibevoice_tts_german.wav",
).to(model.device, model.dtype)
output_ids = model.generate(**inputs)
generated_ids = output_ids[:, inputs["input_ids"].shape[1] :]
transcription = processor.decode(generated_ids, return_format="transcription_only")[0]
print(f"WITHOUT CONTEXT: {transcription}")

# With context
inputs = processor.apply_transcription_request(
    audio="https://huggingface.co/datasets/bezzam/vibevoice_samples/resolve/main/realtime_model/vibevoice_tts_german.wav",
    prompt="About VibeVoice",
).to(model.device, model.dtype)
output_ids = model.generate(**inputs)
generated_ids = output_ids[:, inputs["input_ids"].shape[1] :]
transcription = processor.decode(generated_ids, return_format="transcription_only")[0]
print(f"WITH CONTEXT   : {transcription}")

"""
WITHOUT CONTEXT: Revevoices is a novel framework designed for generating expressive, long-form, multi-speaker conversational audio.
WITH CONTEXT   : VibeVoice is this novel framework designed for generating expressive, long-form, multi-speaker, conversational audio.
"""

from transformers import AutoProcessor, VibeVoiceAsrForConditionalGeneration

model_id = "microsoft/VibeVoice-ASR-HF"
audio = [
    "https://huggingface.co/datasets/bezzam/vibevoice_samples/resolve/main/realtime_model/vibevoice_tts_german.wav",
    "https://huggingface.co/datasets/bezzam/vibevoice_samples/resolve/main/example_output/VibeVoice-1.5B_output.wav"
]
prompts = ["About VibeVoice", None]

processor = AutoProcessor.from_pretrained(model_id)
model = VibeVoiceAsrForConditionalGeneration.from_pretrained(model_id, device_map="auto")
print(f"Model loaded on {model.device} with dtype {model.dtype}")

inputs = processor.apply_transcription_request(audio, prompt=prompts).to(model.device, model.dtype)
output_ids = model.generate(**inputs)
generated_ids = output_ids[:, inputs["input_ids"].shape[1] :]
transcription = processor.decode(generated_ids, return_format="transcription_only")

print(transcription)

from transformers import AutoProcessor, VibeVoiceAsrForConditionalGeneration

tokenizer_chunk_size = 64000    # default is 1440000 (60s @ 24kHz)
model_id = "microsoft/VibeVoice-ASR-HF"
audio = [
    "https://huggingface.co/datasets/bezzam/vibevoice_samples/resolve/main/realtime_model/vibevoice_tts_german.wav",
    "https://huggingface.co/datasets/bezzam/vibevoice_samples/resolve/main/example_output/VibeVoice-1.5B_output.wav"
]
prompts = ["About VibeVoice", None]

processor = AutoProcessor.from_pretrained(model_id)
model = VibeVoiceAsrForConditionalGeneration.from_pretrained(model_id, device_map="auto")
print(f"Model loaded on {model.device} with dtype {model.dtype}")

inputs = processor.apply_transcription_request(audio, prompt=prompts).to(model.device, model.dtype)
output_ids = model.generate(**inputs, tokenizer_chunk_size=tokenizer_chunk_size)
generated_ids = output_ids[:, inputs["input_ids"].shape[1] :]
transcription = processor.decode(generated_ids, return_format="transcription_only")
print(transcription)

from transformers import AutoProcessor, VibeVoiceAsrForConditionalGeneration

model_id = "microsoft/VibeVoice-ASR-HF"
processor = AutoProcessor.from_pretrained(model_id)
model = VibeVoiceAsrForConditionalGeneration.from_pretrained(model_id, device_map="auto")

chat_template = [
    [
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "About VibeVoice"},
                {
                    "type": "audio",
                    "path": "https://huggingface.co/datasets/bezzam/vibevoice_samples/resolve/main/realtime_model/vibevoice_tts_german.wav",
                },
            ],
        }
    ],
    [
        {
            "role": "user",
            "content": [
                {
                    "type": "audio",
                    "path": "https://huggingface.co/datasets/bezzam/vibevoice_samples/resolve/main/example_output/VibeVoice-1.5B_output.wav",
                },
            ],
        }
    ],
]

inputs = processor.apply_chat_template(
    chat_template,
    tokenize=True,
    return_dict=True,
).to(model.device, model.dtype)

output_ids = model.generate(**inputs)
generated_ids = output_ids[:, inputs["input_ids"].shape[1] :]
transcription = processor.decode(generated_ids, return_format="transcription_only")
print(transcription)

from transformers import AutoProcessor, VibeVoiceAsrForConditionalGeneration

model_id = "microsoft/VibeVoice-ASR-HF"
processor = AutoProcessor.from_pretrained(model_id)
model = VibeVoiceAsrForConditionalGeneration.from_pretrained(model_id, device_map="auto")
model.train()

# Prepare batch of 2
# -- NOTE: the original model is trained to output transcription, speaker ID, and timestamps in JSON-like format. Below we are only using the transcription text as the label
chat_template = [
    [
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "VibeVoice is this novel framework designed for generating expressive, long-form, multi-speaker, conversational audio."},
                {
                    "type": "audio",
                    "path": "https://huggingface.co/datasets/bezzam/vibevoice_samples/resolve/main/realtime_model/vibevoice_tts_german.wav",
                },
            ],
        }
    ],
    [
        {
            "role": "user",
            "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",
                    "path": "https://huggingface.co/datasets/bezzam/vibevoice_samples/resolve/main/example_output/VibeVoice-1.5B_output.wav",
                },
            ],
        }
    ],
]
inputs = processor.apply_chat_template(
    chat_template,
    tokenize=True,
    return_dict=True,
    output_labels=True,
).to(model.device, model.dtype)

loss = model(**inputs).loss
print("Loss:", loss.item())
loss.backward()

import time
import torch
from transformers import AutoProcessor, VibeVoiceAsrForConditionalGeneration

model_id = "microsoft/VibeVoice-ASR-HF"

num_warmup = 5
num_runs = 20

# Load processor + model
processor = AutoProcessor.from_pretrained(model_id)
model = VibeVoiceAsrForConditionalGeneration.from_pretrained(model_id, torch_dtype=torch.bfloat16,).to("cuda")

# Prepare static inputs
chat_template = [
    [
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "VibeVoice is this novel framework designed for generating expressive, long-form, multi-speaker, conversational audio.",
                },
                {
                    "type": "audio",
                    "path": "https://huggingface.co/datasets/bezzam/vibevoice_samples/resolve/main/realtime_model/vibevoice_tts_german.wav",
                },
            ],
        }
    ],
] * 4  # batch size 4
inputs = processor.apply_chat_template(
    chat_template,
    tokenize=True,
    return_dict=True,
).to("cuda", torch.bfloat16)

# Benchmark without compile
print("Warming up without compile...")
with torch.no_grad():
    for _ in range(num_warmup):
        _ = model(**inputs)

torch.cuda.synchronize()

print("\nBenchmarking without torch.compile...")
torch.cuda.synchronize()
start = time.time()
with torch.no_grad():
    for _ in range(num_runs):
        _ = model(**inputs)
torch.cuda.synchronize()
no_compile_time = (time.time() - start) / num_runs
print(f"Average time without compile: {no_compile_time:.4f}s")

# Benchmark with compile
print("\nCompiling model...")
model = torch.compile(model)

print("Warming up with compile (includes graph capture)...")
with torch.no_grad():
    for _ in range(num_warmup):
        _ = model(**inputs)

torch.cuda.synchronize()

print("\nBenchmarking with torch.compile...")
torch.cuda.synchronize()
start = time.time()
with torch.no_grad():
    for _ in range(num_runs):
        _ = model(**inputs)
torch.cuda.synchronize()
compile_time = (time.time() - start) / num_runs
print(f"Average time with compile: {compile_time:.4f}s")

speedup = no_compile_time / compile_time
print(f"\nSpeedup: {speedup:.2f}x")

from transformers import pipeline

model_id = "microsoft/VibeVoice-ASR-HF"
pipe = pipeline("any-to-any", model=model_id, device_map="auto")
chat_template = [
    {
        "role": "user",
        "content": [
            {"type": "text", "text": "About VibeVoice"},
            {
                "type": "audio",
                "path": "https://huggingface.co/datasets/bezzam/vibevoice_samples/resolve/main/realtime_model/vibevoice_tts_german.wav",
            },
        ],
    }
]
outputs = pipe(text=chat_template, return_full_text=False)

print("\n" + "=" * 60)
print("RAW PIPELINE OUTPUT")
print("=" * 60)
print(outputs)

"""
============================================================
RAW PIPELINE OUTPUT
============================================================
[{'input_text': [{'role': 'user', 'content': [{'type': 'text', 'text': 'About VibeVoice'}, {'type': 'audio', 'path': 'https://huggingface.co/datasets/bezzam/vibevoice_samples/resolve/main/realtime_model/vibevoice_tts_german.wav'}]}], 'generated_text': 'assistant\n[{"Start":0.0,"End":7.56,"Speaker":0,"Content":"VibeVoice is this novel framework designed for generating expressive, long-form, multi-speaker conversational audio."}]\n'}]
"""