{"_id":"6a9844ce3fd71b944787019d","id":"microsoft/VibeVoice-ASR-Streaming-7B","private":false,"pipeline_tag":"automatic-speech-recognition","library_name":"transformers","tags":["transformers","safetensors","vibevoice","ASR","Transcription","Speech-to-Text","Streaming","automatic-speech-recognition","en","zh","es","pt","de","ja","ko","fr","ru","it","arxiv:2609.02812","license:mit","endpoints_compatible","region:us"],"downloads":1449,"likes":176,"modelId":"microsoft/VibeVoice-ASR-Streaming-7B","author":"microsoft","sha":"60d858b518b4e19d404af3737f848fc185b30177","lastModified":"2026-09-03T05:35:33.000Z","gated":false,"disabled":false,"model-index":null,"config":{"architectures":["VibeVoiceForASRStreamingTraining"],"model_type":"vibevoice","tokenizer_config":{"bos_token":null,"chat_template":"{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {%- if messages[0]['content'] is string %}\n            {{- messages[0]['content'] }}\n        {%- else %}\n            {%- for part in messages[0]['content'] %}\n                {%- if part['type'] == 'text' %}\n                    {{- part['text'] }}\n                {%- elif part['type'] == 'audio' or part['type'] == 'audio_url' %}\n                    {{- '<|AUDIO|>' }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0]['content'] is string %}\n            {{- messages[0]['content'] }}\n        {%- else %}\n            {%- for part in messages[0]['content'] %}\n                {%- if part['type'] == 'text' %}\n                    {{- part['text'] }}\n                {%- elif part['type'] == 'audio' or part['type'] == 'audio_url' %}\n                    {{- '<|AUDIO|>' }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message['content'] is string %}\n            {{- message['content'] }}\n        {%- else %}\n            {%- for part in message['content'] %}\n                {%- if part['type'] == 'text' %}\n                    {{- part['text'] }}\n                {%- elif part['type'] == 'audio' or part['type'] == 'audio_url' %}\n                    {{- '<|AUDIO|>' }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}","eos_token":"<|endoftext|>","pad_token":"<|endoftext|>","unk_token":null}},"cardData":{"language":["en","zh","es","pt","de","ja","ko","fr","ru","it"],"license":"mit","pipeline_tag":"automatic-speech-recognition","tags":["ASR","Transcription","Speech-to-Text","Streaming"],"library_name":"transformers"},"transformersInfo":{"auto_model":"VibeVoiceForASRStreamingTraining","processor":"AutoProcessor"},"siblings":[{"rfilename":".gitattributes"},{"rfilename":"README.md"},{"rfilename":"added_tokens.json"},{"rfilename":"config.json"},{"rfilename":"figures/VibeVoice_ASR_Streaming_architecture.png"},{"rfilename":"figures/VibeVoice_ASR_Streaming_results.png"},{"rfilename":"merges.txt"},{"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":"preprocessor_config.json"},{"rfilename":"special_tokens_map.json"},{"rfilename":"tokenizer.json"},{"rfilename":"tokenizer_config.json"},{"rfilename":"vocab.json"}],"spaces":["microsoft/VibeVoice-ASR-Streaming","yumu908/VibeVoice-ASR-Streaming"],"createdAt":"2026-09-02T15:46:22.000Z","safetensors":{"parameters":{"BF16":8674021857},"total":8674021857},"usedStorage":17349013521}