{"_id":"6a0c1d0b4bbdd3b465441005","id":"OpenMOSS-Team/MOSS-Transcribe-Diarize","private":false,"pipeline_tag":"audio-text-to-text","library_name":"transformers","tags":["transformers","safetensors","moss_transcribe_diarize","text-generation","moss","audio","speech","asr","diarization","timestamp-asr","long-form-audio","multimodal","multilingual","custom_code","audio-text-to-text","en","zh","arxiv:2601.01554","license:apache-2.0","eval-results","region:us"],"downloads":236590,"likes":424,"modelId":"OpenMOSS-Team/MOSS-Transcribe-Diarize","author":"OpenMOSS-Team","sha":"704aa4a9c304e8520be88901e0d1960158ef5b15","lastModified":"2026-09-02T08:46:58.000Z","gated":false,"disabled":false,"model-index":null,"config":{"architectures":["MossTranscribeDiarizeForConditionalGeneration"],"auto_map":{"AutoConfig":"configuration_moss_transcribe_diarize.MossTranscribeDiarizeConfig","AutoModel":"modeling_moss_transcribe_diarize.MossTranscribeDiarizeModel","AutoModelForCausalLM":"modeling_moss_transcribe_diarize.MossTranscribeDiarizeForConditionalGeneration","AutoProcessor":"processing_moss_transcribe_diarize.MossTranscribeDiarizeProcessor"},"model_type":"moss_transcribe_diarize","tokenizer_config":{"bos_token":null,"eos_token":"<|im_end|>","pad_token":"<|endoftext|>","unk_token":null},"chat_template_jinja":"{%- macro render_content(content) -%}\n    {%- if content is string -%}\n        {{- content -}}\n    {%- else -%}\n        {%- for item in content -%}\n            {%- if item.type == 'audio' or 'audio' in item or 'audio_url' in item -%}\n                {{- '<|audio_start|><|audio_pad|><|audio_end|>\\n' -}}\n            {%- elif item.type == 'text' -%}\n                {{- item.text -}}\n            {%- endif -%}\n        {%- endfor -%}\n    {%- endif -%}\n{%- endmacro -%}\n{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- render_content(messages[0].content) + '\\n\\n' }}\n    {%- else %}\n        {{- 'You are a helpful assistant.\\n\\n' }}\n    {%- endif %}\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' + render_content(messages[0].content) + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- set content = render_content(message.content) %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and content is string and not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- set content = render_content(message.content) %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- 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    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}"},"cardData":{"license":"apache-2.0","library_name":"transformers","language":["en","zh"],"tags":["moss","audio","speech","asr","diarization","timestamp-asr","long-form-audio","multimodal","multilingual","custom_code"],"pipeline_tag":"audio-text-to-text"},"transformersInfo":{"auto_model":"AutoModelForCausalLM","custom_class":"modeling_moss_transcribe_diarize.MossTranscribeDiarizeForConditionalGeneration","pipeline_tag":"text-generation"},"siblings":[{"rfilename":".eval_results/open_asr_leaderboard.yaml"},{"rfilename":".gitattributes"},{"rfilename":"Model_Architecture.png"},{"rfilename":"README.md"},{"rfilename":"added_tokens.json"},{"rfilename":"chat_template.jinja"},{"rfilename":"config.json"},{"rfilename":"configuration_moss_transcribe_diarize.py"},{"rfilename":"generation_config.json"},{"rfilename":"merges.txt"},{"rfilename":"model-00000-of-00001.safetensors"},{"rfilename":"model.safetensors.index.json"},{"rfilename":"modeling_moss_transcribe_diarize.py"},{"rfilename":"preprocessor_config.json"},{"rfilename":"processing_moss_transcribe_diarize.py"},{"rfilename":"processor_config.json"},{"rfilename":"special_tokens_map.json"},{"rfilename":"tokenizer.json"},{"rfilename":"tokenizer_config.json"},{"rfilename":"vocab.json"}],"spaces":["hf-audio/open_asr_leaderboard","davanstrien/apollo-11-search","ankandrew/MOSS-Transcribe-Diarize","Luigi/moss-transcribe-diarize-litert","phan-kim-tu/MOSS-transcribe-diarize","Cb1ock/open-asr-leaderboard-moss-transcribe-diarize","hf-audio/open-asr-leaderboard-moss-transcribe-diarize","Marc50000/MOSS-Transcribe-Diarize"],"createdAt":"2026-05-19T08:19:23.000Z","safetensors":{"parameters":{"BF16":908513280},"total":908513280},"usedStorage":3657073722}