{"_id":"69a4fa698d13bda995449bef","id":"microsoft/VibeVoice-ASR-HF","private":false,"pipeline_tag":"audio-text-to-text","library_name":"transformers","tags":["transformers","safetensors","vibevoice_asr","automatic-speech-recognition","ASR","Diarization","Speech-to-Text","Transcription","audio-text-to-text","en","zh","es","pt","de","ja","ko","fr","ru","id","sv","it","he","nl","pl","no","tr","th","ar","hu","ca","cs","da","fa","af","hi","fi","et","aa","el","ro","vi","bg","is","sl","sk","lt","sw","uk","kl","lv","hr","ne","sr","tl","yi","ms","ur","mn","hy","jv","arxiv:2601.18184","license:mit","eval-results","endpoints_compatible","deploy:azure","region:us"],"downloads":51738,"likes":180,"modelId":"microsoft/VibeVoice-ASR-HF","author":"microsoft","sha":"f22241c2062b3b25272bf117397e03d73381037a","lastModified":"2026-03-09T03:11:35.000Z","gated":false,"disabled":false,"model-index":null,"config":{"architectures":["VibeVoiceAsrForConditionalGeneration"],"model_type":"vibevoice_asr","tokenizer_config":{"bos_token":null,"eos_token":"<|endoftext|>","pad_token":"<|endoftext|>","unk_token":null},"chat_template_jinja":"{%- set system_prompt = system_prompt | default(\"You are a helpful assistant that transcribes audio input into text output in JSON format.\") -%}\n<|im_start|>system\n{{ system_prompt }}<|im_end|>\n{%- set audio_token = audio_token | default(\"<|box_start|>\") -%}\n{%- set audio_start_token = \"<|object_ref_start|>\" -%}\n{%- set audio_end_token = \"<|object_ref_end|>\" -%}\n{%- for message in messages -%}\n    {%- if message['role'] == 'user' -%}\n{{ '\n' }}<|im_start|>user{{ '\n' }}{%- set text_items = message['content'] | selectattr('type', 'equalto', 'text') | list -%}\n        {%- set context_text = text_items[0]['text'] if text_items else none -%}\n        {%- for item in message['content'] -%}\n            {%- if item['type'] == 'audio' -%}\n{{ audio_start_token }}{{ audio_token }}{{ audio_end_token }}{{ \"\n\" }}{%- if context_text -%}\nThis is a <|AUDIO_DURATION|> seconds audio, with extra info: {{ context_text }}\n\nPlease transcribe it with these keys: Start time, End time, Speaker ID, Content{%- else -%}\nThis is a <|AUDIO_DURATION|> seconds audio, please transcribe it with these keys: Start time, End time, Speaker ID, Content{%- endif -%}\n            {%- endif -%}\n        {%- endfor -%}\n<|im_end|>{{ '\n' }}\n    {%- endif -%}\n{%- endfor -%}"},"cardData":{"language":["en","zh","es","pt","de","ja","ko","fr","ru","id","sv","it","he","nl","pl","no","tr","th","ar","hu","ca","cs","da","fa","af","hi","fi","et","aa","el","ro","vi","bg","is","sl","sk","lt","sw","uk","kl","lv","hr","ne","sr","tl","yi","ms","ur","mn","hy","jv"],"license":"mit","pipeline_tag":"audio-text-to-text","tags":["ASR","Diarization","Speech-to-Text","Transcription"],"library_name":"transformers"},"transformersInfo":{"auto_model":"AutoModelForMultimodalLM","pipeline_tag":"automatic-speech-recognition","processor":"AutoProcessor"},"siblings":[{"rfilename":".gitattributes"},{"rfilename":"README.md"},{"rfilename":"chat_template.jinja"},{"rfilename":"config.json"},{"rfilename":"figures/DER.jpg"},{"rfilename":"figures/VibeVoice_ASR_archi.png"},{"rfilename":"figures/cpWER.jpg"},{"rfilename":"figures/language_distribution_horizontal.png"},{"rfilename":"figures/tcpWER.jpg"},{"rfilename":"generation_config.json"},{"rfilename":"model-00001-of-00008.safetensors"},{"rfilename":"model-00002-of-00008.safetensors"},{"rfilename":"model-00003-of-00008.safetensors"},{"rfilename":"model-00004-of-00008.safetensors"},{"rfilename":"model-00005-of-00008.safetensors"},{"rfilename":"model-00006-of-00008.safetensors"},{"rfilename":"model-00007-of-00008.safetensors"},{"rfilename":"model-00008-of-00008.safetensors"},{"rfilename":"model.safetensors.index.json"},{"rfilename":"processor_config.json"},{"rfilename":"tokenizer.json"},{"rfilename":"tokenizer_config.json"}],"spaces":["JoshDa-OrionAI/Orion","opedromartins/open_asr_leaderboard_ptbr","paudeoli/vibevoice-asr-studio","libragonxx/vv-sync","LRVSweet/microsoft_vibevoice_asr_demo","ytaliultra/VibeVoice-ASR"],"createdAt":"2026-03-02T02:48:09.000Z","safetensors":{"parameters":{"BF16":8330325888},"total":8330325888},"usedStorage":16694523890}