{"_id":"67bcf3bca03bde20d15377c6","id":"microsoft/Phi-4-multimodal-instruct","private":false,"pipeline_tag":"automatic-speech-recognition","library_name":"transformers","tags":["transformers","safetensors","phi4mm","text-generation","nlp","code","audio","automatic-speech-recognition","speech-summarization","speech-translation","visual-question-answering","phi-4-multimodal","phi","phi-4-mini","custom_code","multilingual","ar","zh","cs","da","nl","en","fi","fr","de","he","hu","it","ja","ko","no","pl","pt","ru","es","sv","th","tr","uk","arxiv:2503.01743","arxiv:2407.13833","license:mit","eval-results","region:us"],"downloads":244060,"likes":1613,"modelId":"microsoft/Phi-4-multimodal-instruct","author":"microsoft","sha":"93f923e1a7727d1c4f446756212d9d3e8fcc5d81","lastModified":"2025-12-10T20:18:10.000Z","gated":false,"disabled":false,"widgetData":[{"example_title":"Librispeech sample 1","src":"https://cdn-media.huggingface.co/speech_samples/sample1.flac"},{"example_title":"Librispeech sample 2","src":"https://cdn-media.huggingface.co/speech_samples/sample2.flac"},{"messages":[{"role":"user","content":"Transcribe the audio to text, and then translate the audio to French. Use <sep> as a separator between the original transcript and the translation."}]}],"model-index":null,"config":{"architectures":["Phi4MMForCausalLM"],"auto_map":{"AutoConfig":"configuration_phi4mm.Phi4MMConfig","AutoModelForCausalLM":"modeling_phi4mm.Phi4MMForCausalLM","AutoTokenizer":"Xenova/gpt-4o"},"model_type":"phi4mm","tokenizer_config":{"bos_token":"<|endoftext|>","chat_template":"{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}","eos_token":"<|endoftext|>","pad_token":"<|endoftext|>","unk_token":"<|endoftext|>"}},"cardData":{"license":"mit","license_link":"https://huggingface.co/microsoft/Phi-4-multimodal-instruct/resolve/main/LICENSE","language":["multilingual","ar","zh","cs","da","nl","en","fi","fr","de","he","hu","it","ja","ko","no","pl","pt","ru","es","sv","th","tr","uk"],"tags":["nlp","code","audio","automatic-speech-recognition","speech-summarization","speech-translation","visual-question-answering","phi-4-multimodal","phi","phi-4-mini"],"widget":[{"example_title":"Librispeech sample 1","src":"https://cdn-media.huggingface.co/speech_samples/sample1.flac"},{"example_title":"Librispeech sample 2","src":"https://cdn-media.huggingface.co/speech_samples/sample2.flac"},{"messages":[{"role":"user","content":"Transcribe the audio to text, and then translate the audio to French. Use <sep> as a separator between the original transcript and the translation."}]}],"library_name":"transformers","paper":"https://arxiv.org/abs/2503.01743"},"transformersInfo":{"auto_model":"AutoModelForCausalLM","custom_class":"modeling_phi4mm.Phi4MMForCausalLM","pipeline_tag":"text-generation"},"siblings":[{"rfilename":".gitattributes"},{"rfilename":"CODE_OF_CONDUCT.md"},{"rfilename":"LICENSE"},{"rfilename":"README.md"},{"rfilename":"SECURITY.md"},{"rfilename":"SUPPORT.md"},{"rfilename":"added_tokens.json"},{"rfilename":"config.json"},{"rfilename":"configuration_phi4mm.py"},{"rfilename":"data_summary_card.md"},{"rfilename":"examples/what_is_shown_in_this_image.wav"},{"rfilename":"examples/what_is_the_traffic_sign_in_the_image.wav"},{"rfilename":"figures/audio_understand.png"},{"rfilename":"figures/multi_image.png"},{"rfilename":"figures/speech_qa.png"},{"rfilename":"figures/speech_recog_by_lang.png"},{"rfilename":"figures/speech_recognition.png"},{"rfilename":"figures/speech_summarization.png"},{"rfilename":"figures/speech_translate.png"},{"rfilename":"figures/speech_translate_2.png"},{"rfilename":"figures/vision_radar.png"},{"rfilename":"generation_config.json"},{"rfilename":"merges.txt"},{"rfilename":"model-00001-of-00003.safetensors"},{"rfilename":"model-00002-of-00003.safetensors"},{"rfilename":"model-00003-of-00003.safetensors"},{"rfilename":"model.safetensors.index.json"},{"rfilename":"modeling_phi4mm.py"},{"rfilename":"phi_4_mm.tech_report.02252025.pdf"},{"rfilename":"preprocessor_config.json"},{"rfilename":"processing_phi4mm.py"},{"rfilename":"processor_config.json"},{"rfilename":"sample_finetune_speech.py"},{"rfilename":"sample_finetune_vision.py"},{"rfilename":"sample_inference_phi4mm.py"},{"rfilename":"special_tokens_map.json"},{"rfilename":"speech-lora/adapter_config.json"},{"rfilename":"speech-lora/adapter_model.safetensors"},{"rfilename":"speech-lora/added_tokens.json"},{"rfilename":"speech-lora/special_tokens_map.json"},{"rfilename":"speech-lora/tokenizer.json"},{"rfilename":"speech-lora/tokenizer_config.json"},{"rfilename":"speech-lora/vocab.json"},{"rfilename":"speech_conformer_encoder.py"},{"rfilename":"tokenizer.json"},{"rfilename":"tokenizer_config.json"},{"rfilename":"vision-lora/adapter_config.json"},{"rfilename":"vision-lora/adapter_model.safetensors"},{"rfilename":"vision-lora/added_tokens.json"},{"rfilename":"vision-lora/special_tokens_map.json"},{"rfilename":"vision-lora/tokenizer.json"},{"rfilename":"vision-lora/tokenizer_config.json"},{"rfilename":"vision-lora/vocab.json"},{"rfilename":"vision_siglip_navit.py"},{"rfilename":"vocab.json"}],"spaces":["eduagarcia/multilingual-tokenizer-leaderboard","AsadIsmail/ternary-quant-demo","ariG23498/phi4-multimodal","TIGER-Lab/MEGA-Bench","MCP-1st-Birthday/Falconzz_M.C.P_Hackathon","microsoft/paza-bench","AudioLLMs/AudioBench-Leaderboard-Extend","VIDraft/PHI4-Multimodal","valira-ai/slo-ocr-benchmark","hchcsuim/Automatic-Speech-Recognition-Speech-to-Text","suanan/Phi-4-multimodal-instruct_test","Xhaheen/Derive_2026_dxb","opedromartins/open_asr_leaderboard_ptbr","huro-ai/GABI-Multimodal-Demo","eddybaraka/nouvas-ai-llm","Xhaheen/Phoenikzz_Apartsearch","jaswanthBreddy/nukropai-farming-ai","acecalisto3/PHI4-Multimodal","grv805/First_agent_template","kedar-bhumkar/video_anamoly_detector","sandsiv/Dashboard_Narrator_Openrouter","akiko19191/BackendOLD","tsphan/llm-token-counter","abdullahalioo/wow","akiko19191/Better_tool_calling","abdullahalioo/vision","abdullahalioo/chats","raffaeleterribile/Final_Assignment","abdullahalioo/wow2","Lovitra/Summariser","maikoz/innovation-catalyst-agent","lakHamza/phi_test","fhsp93/Automatic-Speech-Recognition-Speech-to-Text","gijs/phi4_mm","lordofc/gpt","CanSaragih/Phi-4-multimodal-instruct_test","idsudd/open_asr_leaderboard_cl","Xhaheen/image_hackathon","Xhaheen/Falconzz_MCP_Hackathon","helenai/check-optimum-intel-support","suzmen/gpt4free","bdaibyazad/BDAi-By-Azad","KrishVenky/macro-signal-env","Splend1dchan/Listen-To-The-Latent","bhavesh122/super_AI","vector-institute/HumaniBench","TusharKhitoliya/jarvis-agent","trantrinhminhquan/waifugpt","clamepending/videomemory-demo","ZouZedZed/geni-electrique","Dirbol/VirtForemanBackend","ozdentarikcan/ConvDeck"],"createdAt":"2025-02-24T22:33:32.000Z","safetensors":{"parameters":{"BF16":5574460384},"total":5574460384},"usedStorage":24024633205}