from transformers import AutoProcessor, AutoModelForCausalLM

model_id = "itazap/MOSS-Transcribe-Diarize-HF"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")

audio_url = "https://huggingface.co/datasets/itazap/audio_samples/resolve/main/podcast_sample.wav"
inputs = processor.apply_transcription_request(audio_url)
inputs = inputs.to(model.device, dtype=model.dtype)

outputs = model.generate(**inputs, do_sample=False, max_new_tokens=512)
generated_ids = outputs[:, inputs.input_ids.shape[1] :]

decoded = processor.decode(generated_ids, skip_special_tokens=True)
print("RAW OUTPUT:", decoded)

parsed = processor.decode(generated_ids, return_format="parsed")[0]
print("\nPARSED (list of dicts):")
for segment in parsed:
    print(segment)

transcription = processor.decode(generated_ids, return_format="transcription_only")
print("\nTRANSCRIPTION ONLY:", transcription[0])

"""
RAW OUTPUT: ["[0.48][S01] Hey everyone, welcome back to the show.[2.43][2.46][S01] Today, we're talking about the best way to learn a new skill.[5.22][5.43][S01] I'm here with Jordan to dig into it.[7.14][8.40][S02] Thanks for having me.[9.42][9.63][S02] My take is that consistency beats intensity every single time.[12.87][13.14][S01] That makes sense.[13.92][13.92][S01] Even 20 minutes a day adds up over a few months.[16.17][16.32][S02] Exactly, and writing down small wins keeps you motivated along the way.[19.62]"]

PARSED (list of dicts):
{'Start': 0.48, 'End': 2.43, 'Speaker': 1, 'Content': 'Hey everyone, welcome back to the show.'}
{'Start': 2.46, 'End': 5.22, 'Speaker': 1, 'Content': "Today, we're talking about the best way to learn a new skill."}
{'Start': 5.43, 'End': 7.14, 'Speaker': 1, 'Content': "I'm here with Jordan to dig into it."}
{'Start': 8.4, 'End': 9.42, 'Speaker': 2, 'Content': 'Thanks for having me.'}
{'Start': 9.63, 'End': 12.87, 'Speaker': 2, 'Content': 'My take is that consistency beats intensity every single time.'}
{'Start': 13.14, 'End': 13.92, 'Speaker': 1, 'Content': 'That makes sense.'}
{'Start': 13.92, 'End': 16.17, 'Speaker': 1, 'Content': 'Even 20 minutes a day adds up over a few months.'}
{'Start': 16.32, 'End': 19.62, 'Speaker': 2, 'Content': 'Exactly, and writing down small wins keeps you motivated along the way.'}

TRANSCRIPTION ONLY: Hey everyone, welcome back to the show. Today, we're talking about the best way to learn a new skill. I'm here with Jordan to dig into it. Thanks for having me. My take is that consistency beats intensity every single time. That makes sense. Even 20 minutes a day adds up over a few months. Exactly, and writing down small wins keeps you motivated along the way.
"""

from transformers import AutoProcessor, AutoModelForCausalLM

model_id = "itazap/MOSS-Transcribe-Diarize-HF"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")

audio_url = "https://huggingface.co/datasets/itazap/audio_samples/resolve/main/languages_sample.wav"

# Without keywords
inputs = processor.apply_transcription_request(audio_url)
inputs = inputs.to(model.device, dtype=model.dtype)
outputs = model.generate(**inputs, do_sample=False, max_new_tokens=128)
transcription = processor.decode(outputs[:, inputs.input_ids.shape[1] :], return_format="transcription_only")
print(f"WITHOUT keywords: {transcription[0]}")

# With keywords
inputs = processor.apply_transcription_request(audio_url, keywords=["Mandarin", "Yorùbá"])
inputs = inputs.to(model.device, dtype=model.dtype)
outputs = model.generate(**inputs, do_sample=False, max_new_tokens=128)
transcription = processor.decode(outputs[:, inputs.input_ids.shape[1] :], return_format="transcription_only")
print(f"WITH keywords   : {transcription[0]}")

"""
WITHOUT keywords: Let's talk about the most spoken languages in the world. Mandarin Chinese has the most native speakers, followed by Spanish, English, and Hindi. In West Africa, one of the most widely spoken languages is Yoruba, with over 50 million speakers.
WITH keywords   : Let's talk about the most spoken languages in the world. Mandarin Chinese has the most native speakers, followed by Spanish, English, and Hindi. In West Africa, one of the most widely spoken languages is Yorùbá, with over 50 million speakers.
"""

from transformers import AutoProcessor, AutoModelForCausalLM

model_id = "itazap/MOSS-Transcribe-Diarize-HF"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")

audio_url = "https://huggingface.co/datasets/itazap/audio_samples/resolve/main/intro_sample.wav"
conversation = [
    {
        "role": "user",
        "content": [
            {"type": "audio", "url": audio_url},
        ],
    },
]

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

outputs = model.generate(**inputs, do_sample=False, max_new_tokens=128)
decoded = processor.decode(
    outputs[:, inputs.input_ids.shape[1] :],
    skip_special_tokens=True,
)
print(decoded)

from transformers import AutoProcessor, AutoModelForCausalLM

model_id = "itazap/MOSS-Transcribe-Diarize-HF"
processor = AutoProcessor.from_pretrained(model_id)
# `from_pretrained` is used here for convenience, the model can also be built from a config directly.
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")

audio = [
    "https://huggingface.co/datasets/itazap/audio_samples/resolve/main/intro_sample.wav",
    "https://huggingface.co/datasets/itazap/audio_samples/resolve/main/languages_sample.wav",
]
keywords = [None, ["Mandarin", "Yorùbá"]]

inputs = processor.apply_transcription_request(audio, keywords=keywords)
inputs = inputs.to(model.device, dtype=model.dtype)
outputs = model.generate(**inputs, do_sample=False, max_new_tokens=128)
transcription = processor.decode(outputs[:, inputs.input_ids.shape[1] :], return_format="transcription_only")
print(transcription)

from transformers import AutoModelForCausalLM, AutoProcessor

model_id = "itazap/MOSS-Transcribe-Diarize-HF"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
model.train()

audio_url = "https://huggingface.co/datasets/itazap/audio_samples/resolve/main/intro_sample.wav"
transcription = (
    "[0.00][S01] Welcome to this demonstration of automatic speech recognition and speaker diarization using an "
    "end-to-end transformer model.[7.47]"
)

inputs = processor.apply_transcription_request(audio_url, transcription=transcription)
inputs.to(model.device, dtype=model.dtype)

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

import time

import torch

from transformers import AutoProcessor, AutoModelForCausalLM


model_id = "itazap/MOSS-Transcribe-Diarize-HF"

num_warmup = 5
num_runs = 20

# Load processor + model
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id).to("cuda")

# Prepare static inputs
audio_url = "https://huggingface.co/datasets/itazap/audio_samples/resolve/main/intro_sample.wav"
inputs = processor.apply_transcription_request([audio_url] * 4).to(model.device, torch.bfloat16)

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

torch.accelerator.synchronize()

print("\nBenchmarking without torch.compile...")
torch.accelerator.synchronize()
start = time.time()
with torch.no_grad():
    for _ in range(num_runs):
        _ = model(**inputs)
torch.accelerator.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.accelerator.synchronize()

print("\nBenchmarking with torch.compile...")
torch.accelerator.synchronize()
start = time.time()
with torch.no_grad():
    for _ in range(num_runs):
        _ = model(**inputs)
torch.accelerator.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")

import torch
from transformers import AutoProcessor, AutoModelForCausalLM, CompileConfig

model_id = "itazap/MOSS-Transcribe-Diarize-HF"
num_warmup = 3

processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id).to("cuda")

audio_url = "https://huggingface.co/datasets/itazap/audio_samples/resolve/main/intro_sample.wav"
inputs = processor.apply_transcription_request([audio_url] * 4).to(model.device, torch.bfloat16)

compile_config = CompileConfig()

# Warmup
for _ in range(num_warmup):
    _ = model.generate(**inputs, max_new_tokens=128, cache_implementation="static", compile_config=compile_config)

# Apply model
generated_ids = model.generate(
    **inputs, max_new_tokens=128, cache_implementation="static", compile_config=compile_config
)
transcription = processor.decode(generated_ids[:, inputs.input_ids.shape[1] :], return_format="transcription_only")
print(transcription)