GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
bezzam
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
bezzam
Model Tree
Input Modalities
Output Modalities
Supported Functionality
The Qwen3-ASR family includes Qwen3-ASR-1.7B and Qwen3-ASR-0.6B, which support language identification and ASR for 52 languages and dialects. Both leverage large-scale speech training data and the strong audio understanding capability of their foundation model, Qwen3-Omni. The 1.7B version achieves state-of-the-art performance among open-source ASR models and is competitive with the strongest proprietary commercial APIs.
Key features:
| Model | Supported Languages | Supported Dialects | Inference Mode | Audio Types |
|---|---|---|---|---|
| Qwen/Qwen3-ASR-1.7B-hf & Qwen/Qwen3-ASR-0.6B-hf | Chinese (zh), English (en), Cantonese (yue), Arabic (ar), German (de), French (fr), Spanish (es), Portuguese (pt), Indonesian (id), Italian (it), Korean (ko), Russian (ru), Thai (th), Vietnamese (vi), Japanese (ja), Turkish (tr), Hindi (hi), Malay (ms), Dutch (nl), Swedish (sv), Danish (da), Finnish (fi), Polish (pl), Czech (cs), Filipino (fil), Persian (fa), Greek (el), Hungarian (hu), Macedonian (mk), Romanian (ro) | Anhui, Dongbei, Fujian, Gansu, Guizhou, Hebei, Henan, Hubei, Hunan, Jiangxi, Ningxia, Shandong, Shaanxi, Shanxi, Sichuan, Tianjin, Yunnan, Zhejiang, Cantonese (HK), Cantonese (Guangdong), Wu, Minnan | Offline / Streaming | Speech, Singing Voice, Songs with BGM |
| Qwen/Qwen3-ForcedAligner-0.6B-hf | Chinese, English, Cantonese, French, German, Italian, Japanese, Korean, Portuguese, Russian, Spanish | — | NAR | Speech |
Qwen3-ASR is supported natively in 🤗 Transformers. Until it is part of an official Transformers release, install from source:
bash
pip install git+https://github.com/huggingface/transformersapply_transcription_request handles chat-template formatting for you and is the recommended entry point.
python
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://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_en.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> markerraw = 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 texttranscription = 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."""Pass a language hint to skip auto-detection.
python
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://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_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 language hint (language code or full name both accepted)inputs = processor.apply_transcription_request( audio="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_zh.wav", language="Chinese", # or "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"With hint: {processor.decode(generated_ids, return_format='transcription_only')[0]}")Pass a list of audio paths and optional languages to transcribe multiple files in one call.
python
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") audio = [ "https://huggingface.co/datasets/bezzam/audio_samples/resolve/main/librispeech_mr_quilter.wav", "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_zh.wav",] inputs = processor.apply_transcription_request( audio, language=[None, "zh"],).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}")apply_transcription_request is a convenience wrapper around apply_chat_template. Use the chat template directly for more control, such as providing a language hint via a system message.
python
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 = [ [ {"role": "system", "content": [{"type": "text", "text": "English"}]}, { "role": "user", "content": [ { "type": "audio", "path": "https://huggingface.co/datasets/bezzam/audio_samples/resolve/main/librispeech_mr_quilter.wav", }, ], }, ], [ { "role": "user", "content": [ { "type": "audio", "path": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_zh.wav", }, ], }, ],] inputs = processor.apply_chat_template( chat_template, tokenize=True, return_dict=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)python
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")model.train() chat_template = [ [ { "role": "user", "content": [ { "type": "text", "text": "Mr. Quilter is the apostle of the middle classes, and we are glad to welcome his gospel.", }, { "type": "audio", "path": "https://huggingface.co/datasets/bezzam/audio_samples/resolve/main/librispeech_mr_quilter.wav", }, ], } ],] inputs = processor.apply_chat_template( chat_template, tokenize=True, return_dict=True, output_labels=True,).to(model.device, model.dtype) loss = model(**inputs).lossprint("Loss:", loss.item())loss.backward()Use Qwen3ASRForTokenClassification to obtain word-level timestamps from a transcript. Transcribe first with the ASR model, then align with the forced aligner.
Supported languages: Chinese, English, Cantonese, French, German, Italian, Japanese, Korean, Portuguese, Russian, Spanish.
Japanese requires
nagisaand Korean requiressoynlp:pip install nagisa soynlp
python
import torchfrom 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: Transcribeinputs = 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 inputsaligner_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 alignerwith torch.inference_mode(): outputs = aligner_model(**aligner_inputs) # Step 4: Decode timestampstimestamps = 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 0.800Quilter 0.800 1.280is 1.280 1.440the 1.440 1.520apostle 1.520 2.080..."""python
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"] # Use processor helper to extract transcriptiontranscription = pipe.processor.extract_transcription(raw_text)print(f"Transcription: {transcription}")Both the ASR and forced aligner models support torch.compile. The forced aligner is a particularly good fit because it runs a single forward pass with no autoregressive decoding, making it ideal for bulk timestamping workflows.
On an A100 we observed ~2.5× speed-up for the forced aligner and ~2.4× for ASR generate at batch size 4.
python
import torchfrom transformers import AutoProcessor, AutoModelForMultimodalLM model_id = "Qwen/Qwen3-ASR-1.7B-hf"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,).to("cuda", torch.bfloat16) model.forward = torch.compile(model.forward) # Warmupwith torch.inference_mode(): for _ in range(3): _ = model.generate(**inputs, max_new_tokens=256, do_sample=False) # Inferencewith torch.inference_mode(): output_ids = model.generate(**inputs, max_new_tokens=256, do_sample=False) generated_ids = output_ids[:, inputs["input_ids"].shape[1]:]print(processor.decode(generated_ids, return_format="transcription_only")[0])WER on the HuggingFace Open ASR Leaderboard:
| Model | Mean WER | AMI | Earnings22 | GigaSpeech | LS Clean | LS Other | SPGISpeech | VoxPopuli |
|---|---|---|---|---|---|---|---|---|
| Qwen3-ASR-1.7B-hf | 5.59 | 9.26 | 9.88 | 7.25 | 1.24 | 2.92 | 2.58 | 5.99 |
| Qwen3-ASR-0.6B-hf | 6.31 |
bibtex
@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}}| 10.57 |
| 10.72 |
| 7.65 |
| 1.69 |
| 3.97 |
| 2.74 |
| 6.80 |