Qwen3-ForcedAligner-0.6B-hf

pip install git+https://github.com/huggingface/transformers

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="cuda",
)

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="cuda",
)

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")

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("cuda", torch.bfloat16)

model.forward = torch.compile(model.forward)

# Warmup
with torch.no_grad():
    for _ in range(num_warmup):
        _ = model(**aligner_inputs)

# Inference
with torch.no_grad():
    outputs = model(**aligner_inputs)

@article{Qwen3-ASR,
  title={Qwen3-ASR Technical Report},
  author={Xian Shi, Xiong Wang, Zhifang Guo, Yongqi Wang, Pei Zhang, Xinyu Zhang, Zishan Guo,
          Hongkun Hao, Yu Xi, Baosong Yang, Jin Xu, Jingren Zhou, Junyang Lin},
  journal={arXiv preprint arXiv:2601.21337},
  year={2026}
}