from transformers import AutoProcessor, AutoModelForMultimodalLM

model_id = "Qwen/Qwen3-ASR-1.7B-hf"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForMultimodalLM.from_pretrained(model_id, device_map="auto")
print(f"Model loaded on {model.device} with dtype {model.dtype}")

inputs = processor.apply_transcription_request(
    audio="https://huggingface.co/datasets/bezzam/audio_samples/resolve/main/librispeech_mr_quilter.wav",
).to(model.device, model.dtype)

output_ids = model.generate(**inputs, max_new_tokens=256)
generated_ids = output_ids[:, inputs["input_ids"].shape[1]:]

# Raw output includes language tag and <asr_text> marker
raw = processor.decode(generated_ids)[0]
print(f"Raw: {raw}")

# Parsed output: dict with "language" and "transcription"
parsed = processor.decode(generated_ids, return_format="parsed")[0]
print(f"Parsed: {parsed}")

# Extract only the transcription text
transcription = processor.decode(generated_ids, return_format="transcription_only")[0]
print(f"Transcription: {transcription}")

"""
Raw: language English<asr_text>Mr. Quilter is the apostle of the middle classes, and we are glad to welcome his gospel.
Parsed: {'language': 'English', 'transcription': 'Mr. Quilter is the apostle of the middle classes, and we are glad to welcome his gospel.'}
Transcription: Mr. Quilter is the apostle of the middle classes, and we are glad to welcome his gospel.
"""

from transformers import AutoProcessor, AutoModelForMultimodalLM

model_id = "Qwen/Qwen3-ASR-1.7B-hf"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForMultimodalLM.from_pretrained(model_id, device_map="auto")

# Without language hint (auto-detect)
inputs = processor.apply_transcription_request(
    audio="https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/mandarin_voxcpm_zh.wav",
).to(model.device, model.dtype)
output_ids = model.generate(**inputs, max_new_tokens=256)
generated_ids = output_ids[:, inputs["input_ids"].shape[1]:]
print(f"Auto-detect: {processor.decode(generated_ids, return_format='transcription_only')[0]}")

# With forced language
inputs = processor.apply_transcription_request(
    audio="https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/mandarin_voxcpm_zh.wav",
    language="Chinese",  # or language code "zh"
).to(model.device, model.dtype)
output_ids = model.generate(**inputs, max_new_tokens=256)
generated_ids = output_ids[:, inputs["input_ids"].shape[1]:]
print(f"Forced:      {processor.decode(generated_ids, return_format='transcription_only')[0]}")

from transformers import AutoProcessor, AutoModelForMultimodalLM

model_id = "Qwen/Qwen3-ASR-1.7B-hf"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForMultimodalLM.from_pretrained(model_id, device_map="auto")

inputs = processor.apply_transcription_request(
    audio="https://huggingface.co/datasets/bezzam/audio_samples/resolve/main/librispeech_mr_quilter.wav",
    prompt="Vocabulary: Quilter, apostle, gospel.",
    language="English",
).to(model.device, model.dtype)

output_ids = model.generate(**inputs, max_new_tokens=256)
generated_ids = output_ids[:, inputs["input_ids"].shape[1]:]
print(processor.decode(generated_ids, return_format="transcription_only")[0])

from transformers import AutoProcessor, AutoModelForMultimodalLM

model_id = "Qwen/Qwen3-ASR-1.7B-hf"
audio = [
    "https://huggingface.co/datasets/bezzam/audio_samples/resolve/main/librispeech_mr_quilter.wav",
    "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/mandarin_voxcpm_zh.wav",
]

processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForMultimodalLM.from_pretrained(model_id, device_map="auto")

inputs = processor.apply_transcription_request(
    audio,
    prompt=["Vocabulary: Quilter, apostle, gospel.", None],
    language=[None, "zh"],  # language codes ("zh") and full names ("Chinese") are both accepted
).to(model.device, model.dtype)

output_ids = model.generate(**inputs, max_new_tokens=256)
generated_ids = output_ids[:, inputs["input_ids"].shape[1]:]
transcriptions = processor.decode(generated_ids, return_format="transcription_only")

for i, text in enumerate(transcriptions):
    print(f"Audio {i + 1}: {text}")

from transformers import AutoProcessor, Qwen3ASRForConditionalGeneration

model_id = "Qwen/Qwen3-ASR-1.7B-hf"
processor = AutoProcessor.from_pretrained(model_id)
model = Qwen3ASRForConditionalGeneration.from_pretrained(model_id, device_map="auto")

chat_template = [
    [
        # Context/hotwords as system message
        {"role": "system", "content": [{"type": "text", "text": "Vocabulary: Quilter, apostle, gospel."}]},
        {
            "role": "user",
            "content": [
                {
                    "type": "audio",
                    "path": "https://huggingface.co/datasets/bezzam/audio_samples/resolve/main/librispeech_mr_quilter.wav",
                },
            ],
        },
        # empty prefill since forcing language in the other sample
        {"role": "assistant", "content": [{"type": "text", "text": ""}]},
    ],
    [
        {
            "role": "user",
            "content": [
                {
                    "type": "audio",
                    "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/mandarin_voxcpm_zh.wav",
                },
            ],
        },
        {"role": "assistant", "content": [{"type": "text", "text": "language Chinese<asr_text>"}]},
    ],
]

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

output_ids = model.generate(**inputs, max_new_tokens=256)
generated_ids = output_ids[:, inputs["input_ids"].shape[1]:]
transcriptions = processor.decode(generated_ids, return_format="transcription_only")
for text in transcriptions:
    print(text)

from datasets import Audio, load_dataset
from transformers import AutoProcessor, Qwen3ASRForConditionalGeneration

model_id = "Qwen/Qwen3-ASR-1.7B-hf"
NUM_SAMPLES = 2

processor = AutoProcessor.from_pretrained(model_id)
model = Qwen3ASRForConditionalGeneration.from_pretrained(model_id, device_map="auto")
model.train()

ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
ds = ds.cast_column("audio", Audio(sampling_rate=processor.feature_extractor.sampling_rate))
speech_samples = [el["array"] for el in ds["audio"][:NUM_SAMPLES]]
text_samples = ds["text"][:NUM_SAMPLES]

inputs = processor.apply_transcription_request(speech_samples, language="en", transcription=text_samples)
inputs.to(model.device, dtype=model.dtype)

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

pip install nagisa soynlp

import torch
from transformers import AutoProcessor, AutoModelForMultimodalLM, AutoModelForTokenClassification

asr_model_id = "Qwen/Qwen3-ASR-0.6B-hf"
aligner_model_id = "Qwen/Qwen3-ForcedAligner-0.6B-hf"

asr_processor = AutoProcessor.from_pretrained(asr_model_id)
asr_model = AutoModelForMultimodalLM.from_pretrained(asr_model_id, device_map="auto")

aligner_processor = AutoProcessor.from_pretrained(aligner_model_id)
aligner_model = AutoModelForTokenClassification.from_pretrained(
    aligner_model_id, dtype=torch.bfloat16, device_map="auto"
)

audio_url = "https://huggingface.co/datasets/bezzam/audio_samples/resolve/main/librispeech_mr_quilter.wav"

# Step 1: Transcribe
inputs = asr_processor.apply_transcription_request(audio=audio_url)
inputs = inputs.to(asr_model.device, asr_model.dtype)
output_ids = asr_model.generate(**inputs, max_new_tokens=256)
generated_ids = output_ids[:, inputs["input_ids"].shape[1]:]
parsed = asr_processor.decode(generated_ids, return_format="parsed")[0]
transcript = parsed["transcription"]
language = parsed["language"] or "English"

# Step 2: Prepare alignment inputs
aligner_inputs, word_lists = aligner_processor.prepare_forced_aligner_inputs(
    audio=audio_url, transcript=transcript, language=language,
)
aligner_inputs = aligner_inputs.to(aligner_model.device, aligner_model.dtype)

# Step 3: Run forced aligner
with torch.inference_mode():
    outputs = aligner_model(**aligner_inputs)

# Step 4: Decode timestamps
timestamps = aligner_processor.decode_forced_alignment(
    logits=outputs.logits,
    input_ids=aligner_inputs["input_ids"],
    word_lists=word_lists,
    timestamp_token_id=aligner_model.config.timestamp_token_id,
)[0]

for item in timestamps:
    print(f"{item['text']:<20} {item['start_time']:>8.3f}s → {item['end_time']:>8.3f}s")

"""
Word                  Start (s)    End (s)
------------------------------------------
Mr                        0.560      0.800
Quilter                   0.800      1.280
is                        1.280      1.440
the                       1.440      1.520
apostle                   1.520      2.080
...
"""

import torch
from datasets import Audio, load_dataset
from transformers import AutoModelForCTC, AutoProcessor, AutoModelForTokenClassification

parakeet_processor = AutoProcessor.from_pretrained("nvidia/parakeet-ctc-1.1b")
parakeet_model = AutoModelForCTC.from_pretrained(
    "nvidia/parakeet-ctc-1.1b", dtype="auto", device_map="auto",
)

aligner_model_id = "Qwen/Qwen3-ForcedAligner-0.6B-hf"
aligner_processor = AutoProcessor.from_pretrained(aligner_model_id)
aligner_model = AutoModelForTokenClassification.from_pretrained(
    aligner_model_id, dtype=torch.bfloat16, device_map="auto",
)

ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
ds = ds.cast_column("audio", Audio(sampling_rate=parakeet_processor.feature_extractor.sampling_rate))
audio_arrays = [ds[i]["audio"]["array"] for i in range(3)]
sr = ds[0]["audio"]["sampling_rate"]

# Batch transcribe with Parakeet
inputs = parakeet_processor(audio_arrays, sampling_rate=sr, return_tensors="pt", padding=True).to(
    parakeet_model.device, dtype=parakeet_model.dtype
)
with torch.inference_mode():
    outputs = parakeet_model.generate(**inputs)
transcripts = parakeet_processor.decode(outputs)

# Batch align with Qwen3 Forced Aligner
aligner_inputs, word_lists = aligner_processor.prepare_forced_aligner_inputs(
    audio=audio_arrays, transcript=transcripts, language="English",
)
aligner_inputs = aligner_inputs.to(aligner_model.device, aligner_model.dtype)

with torch.inference_mode():
    aligner_outputs = aligner_model(**aligner_inputs)

batch_timestamps = aligner_processor.decode_forced_alignment(
    logits=aligner_outputs.logits,
    input_ids=aligner_inputs["input_ids"],
    word_lists=word_lists,
    timestamp_token_id=aligner_model.config.timestamp_token_id,
)

for i, (transcript, timestamps) in enumerate(zip(transcripts, batch_timestamps)):
    print(f"\n[Sample {i}] {transcript}")
    for item in timestamps[:5]:
        print(f"  {item['text']:<20} {item['start_time']:>8.3f}s → {item['end_time']:>8.3f}s")
    if len(timestamps) > 5:
        print(f"  ... ({len(timestamps) - 5} more words)")

import torch
from transformers import AutoProcessor, AutoModelForTokenClassification

model_id = "Qwen/Qwen3-ForcedAligner-0.6B-hf"
num_warmup = 5
batch_size = 4

processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForTokenClassification.from_pretrained(model_id, dtype=torch.bfloat16).to("cuda")

# Prepare a batch of 4 samples
audio_url = "https://huggingface.co/datasets/bezzam/audio_samples/resolve/main/librispeech_mr_quilter.wav"
transcript = "Mr. Quilter is the apostle of the middle classes."

aligner_inputs, word_lists = processor.prepare_forced_aligner_inputs(
    audio=[audio_url] * batch_size,
    transcript=[transcript] * batch_size,
    language=["English"] * batch_size,
)
aligner_inputs = aligner_inputs.to(model.device, torch.bfloat16)

# Warm-up and apply model
model = torch.compile(model)
with torch.no_grad():
    for _ in range(num_warmup):
        _ = model(**aligner_inputs)
with torch.no_grad():
    _ = model(**aligner_inputs)

import torch
from transformers import AutoProcessor, AutoModelForMultimodalLM, CompileConfig

model_id = "Qwen/Qwen3-ASR-1.7B-hf"
num_warmup = 3
max_new_tokens = 256

processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForMultimodalLM.from_pretrained(model_id, dtype=torch.bfloat16).to("cuda").eval()

audio_url = "https://huggingface.co/datasets/bezzam/audio_samples/resolve/main/librispeech_mr_quilter.wav"
inputs = processor.apply_transcription_request(
    audio=[audio_url] * 4,  # batch of 4
).to(model.device, torch.bfloat16)

compile_config = CompileConfig()

# Warmup
with torch.inference_mode():
    for _ in range(num_warmup):
        _ = model.generate(
            **inputs, max_new_tokens=max_new_tokens, do_sample=False,
            cache_implementation="static", compile_config=compile_config,
        )
torch.cuda.synchronize()

# Apply model
with torch.inference_mode():
    output_ids = model.generate(
        **inputs, max_new_tokens=max_new_tokens, do_sample=False,
        cache_implementation="static", compile_config=compile_config,
    )
generated_ids = output_ids[:, inputs["input_ids"].shape[1] :]
text_compiled = processor.decode(generated_ids, return_format="transcription_only")[0]
print(f"Output:  {text_compiled}")

from transformers import pipeline

model_id = "Qwen/Qwen3-ASR-1.7B-hf"
pipe = pipeline("any-to-any", model=model_id, device_map="auto")

chat_template = [
    {
        "role": "user",
        "content": [
            {
                "type": "audio",
                "path": "https://huggingface.co/datasets/bezzam/audio_samples/resolve/main/librispeech_mr_quilter.wav",
            },
        ],
    }
]
outputs = pipe(text=chat_template, return_full_text=False)
raw_text = outputs[0]["generated_text"]
print(f"Raw: {raw_text}")

# Use processor helper to extract transcription
transcription = pipe.processor.extract_transcription(raw_text)
print(f"Transcription: {transcription}")