{"_id":"63314c44fece0490c3c94e60","id":"openai/whisper-medium","private":false,"pipeline_tag":"automatic-speech-recognition","library_name":"transformers","tags":["transformers","pytorch","tf","jax","safetensors","whisper","automatic-speech-recognition","audio","hf-asr-leaderboard","en","zh","de","es","ru","ko","fr","ja","pt","tr","pl","ca","nl","ar","sv","it","id","hi","fi","vi","he","uk","el","ms","cs","ro","da","hu","ta","no","th","ur","hr","bg","lt","la","mi","ml","cy","sk","te","fa","lv","bn","sr","az","sl","kn","et","mk","br","eu","is","hy","ne","mn","bs","kk","sq","sw","gl","mr","pa","si","km","sn","yo","so","af","oc","ka","be","tg","sd","gu","am","yi","lo","uz","fo","ht","ps","tk","nn","mt","sa","lb","my","bo","tl","mg","as","tt","haw","ln","ha","ba","jw","su","arxiv:2212.04356","license:apache-2.0","model-index","endpoints_compatible","deploy:sagemaker","deploy:azure","region:us"],"downloads":328922,"likes":298,"modelId":"openai/whisper-medium","author":"openai","sha":"abdf7c39ab9d0397620ccaea8974cc764cd0953e","lastModified":"2024-02-29T10:57:42.000Z","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"}],"model-index":[{"name":"whisper-medium","results":[{"task":{"name":"Automatic Speech Recognition","type":"automatic-speech-recognition"},"dataset":{"name":"LibriSpeech (clean)","type":"librispeech_asr","config":"clean","split":"test","args":{"language":"en"}},"metrics":[{"name":"Test WER","type":"wer","value":2.9,"verified":false}]},{"task":{"name":"Automatic Speech Recognition","type":"automatic-speech-recognition"},"dataset":{"name":"LibriSpeech (other)","type":"librispeech_asr","config":"other","split":"test","args":{"language":"en"}},"metrics":[{"name":"Test WER","type":"wer","value":5.9,"verified":false}]},{"task":{"name":"Automatic Speech Recognition","type":"automatic-speech-recognition"},"dataset":{"name":"Common Voice 11.0","type":"mozilla-foundation/common_voice_11_0","config":"hi","split":"test","args":{"language":"hi"}},"metrics":[{"name":"Test WER","type":"wer","value":53.87,"verified":false}]}]}],"config":{"architectures":["WhisperForConditionalGeneration"],"model_type":"whisper","tokenizer_config":{"bos_token":"<|endoftext|>","eos_token":"<|endoftext|>","pad_token":"<|endoftext|>","unk_token":"<|endoftext|>"}},"cardData":{"language":["en","zh","de","es","ru","ko","fr","ja","pt","tr","pl","ca","nl","ar","sv","it","id","hi","fi","vi","he","uk","el","ms","cs","ro","da","hu","ta","no","th","ur","hr","bg","lt","la","mi","ml","cy","sk","te","fa","lv","bn","sr","az","sl","kn","et","mk","br","eu","is","hy","ne","mn","bs","kk","sq","sw","gl","mr","pa","si","km","sn","yo","so","af","oc","ka","be","tg","sd","gu","am","yi","lo","uz","fo","ht","ps","tk","nn","mt","sa","lb","my","bo","tl","mg","as","tt","haw","ln","ha","ba","jw","su"],"tags":["audio","automatic-speech-recognition","hf-asr-leaderboard"],"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"}],"model-index":[{"name":"whisper-medium","results":[{"task":{"name":"Automatic Speech Recognition","type":"automatic-speech-recognition"},"dataset":{"name":"LibriSpeech (clean)","type":"librispeech_asr","config":"clean","split":"test","args":{"language":"en"}},"metrics":[{"name":"Test WER","type":"wer","value":2.9,"verified":false}]},{"task":{"name":"Automatic Speech Recognition","type":"automatic-speech-recognition"},"dataset":{"name":"LibriSpeech (other)","type":"librispeech_asr","config":"other","split":"test","args":{"language":"en"}},"metrics":[{"name":"Test WER","type":"wer","value":5.9,"verified":false}]},{"task":{"name":"Automatic Speech Recognition","type":"automatic-speech-recognition"},"dataset":{"name":"Common Voice 11.0","type":"mozilla-foundation/common_voice_11_0","config":"hi","split":"test","args":{"language":"hi"}},"metrics":[{"name":"Test WER","type":"wer","value":53.87,"verified":false}]}]}],"pipeline_tag":"automatic-speech-recognition","license":"apache-2.0"},"transformersInfo":{"auto_model":"AutoModelForSpeechSeq2Seq","pipeline_tag":"automatic-speech-recognition","processor":"AutoProcessor"},"siblings":[{"rfilename":".gitattributes"},{"rfilename":"README.md"},{"rfilename":"added_tokens.json"},{"rfilename":"config.json"},{"rfilename":"flax_model.msgpack"},{"rfilename":"generation_config.json"},{"rfilename":"merges.txt"},{"rfilename":"model.safetensors"},{"rfilename":"normalizer.json"},{"rfilename":"preprocessor_config.json"},{"rfilename":"pytorch_model.bin"},{"rfilename":"special_tokens_map.json"},{"rfilename":"tf_model.h5"},{"rfilename":"tokenizer.json"},{"rfilename":"tokenizer_config.json"},{"rfilename":"vocab.json"}],"spaces":["mteb/leaderboard","elmresearchcenter/open_universal_arabic_asr_leaderboard","Plachta/VALL-E-X","OpenSound/CapSpeech-TTS","kadirnar/Audio-WebUI","cstr/transcribe_audio","gobeldan/insanely-fast-whisper-webui","devilent2/whisper-v3-zero","kadirnar/Whisper_M2M100_BioGpt","ardha27/Youtube-AI-Summarizer","radinhas/hf-llm-api","mozilla-ai/transcribe","msalhab96/open_universal_arabic_asr_leaderboard_all","innev/whisper-Base","sepioo/facebook-translation","hchcsuim/Automatic-Speech-Recognition-Speech-to-Text","yangzhang33/GreekMMLU-Leaderboard","CeibalUY/transcribir_audio","TaiYouWeb/whisper-multi-model","Tlanextli/Speech2Text_Multi","devilent2/whisper-v3-zero-dev","beeguy/voice-to-text","Woziii/scribe","ardha27/VideoAnalyzer","Johnyquest7/medical-transcription-notes","awacke1/ASR-openai-whisper-large","Ericboi229-gmx-co-uk/insanely-fast-whisper-webui","logeshnusic/transcribe_audio","feliksius/ai-translation","Speedofmastery/orynxml-backend","Yash030/claude-code-proxy","build-small-hackathon/Yui-home-assistant","ArtFix0/speech-to-speech-dashboard","osanseviero/whisper-medium","EnigmaOfTheWorld/GenZBot","Basav/openai-whisper-medium","jpdiazpardo/jpdiazpardo-whisper-tiny-metal","vikfand/stable-whisper-v3","207ss/VALL-E-X","filben/transcrever_audio_pt","NSect/VALL-E-X","ruslanmv/hf-llm-api-collection","devilent2/whisper-v3-zero-canary","barrylevn/hf-llm-api","fcernafukuzaki/speech_recognition_pipeline","marioluciofjr/voxsense","soumitra144/VibeScribe","soiz1/VALL-E-X3","tejash300/doc_analyzer","pareek-voicearena/test-hindi-2","RamaGanteng/kiddygoo-ai","tilakgupta2005/Wishper","blkrabbit/urltranscribe","moradmoqbel/STT","rizwan171111/my-whisper-app","Sushant-Kumar-Sinha/speech-to-speech-translator","Krishna346/Youtube-summarizer-api","baimkita/clipviral","Umong/MayerBhasha","r4k5O/deepsite-project-l9y0q","aidn/yapper","nabil6391/bengali-asr-leaderboard","maxpar1/leaderboard","nikrif410/transcribe_audio","tillu-AI/tillu-unified","DINESH210805/tamil-asr-transliteration","Asem75/My_teacher_lesson","rsinhacabi/llms-huggingface","build-small-hackathon/awaaz","dennis-9/voiceaid-health-backend","supermy/whisper-medium","Anustup/pyanote","joebyron44/openai-whisper-medium","awacke1/ASR-openai-whisper-medium","vanping/openai-whisper-medium","RedExergy/openai-whisper-medium","Mikky/openai-whisper-medium","HexinZhang/openai-whisper-medium","Rajab123/openai-whisper-medium","ericckfeng/whisper-Base-Clone","monim/openai-whisper-medium","rocky963/aiapp","Cathaltwo/speechtotext","aieye/speech_recognition_tutorial","awacke1/openai-whisper-medium","Rakib/Bangla_ASR_Demo","futranbg/S2T","hiwei/asr-hf-api","wang0507/my_first_space","pablocst/asr-hf-api","smidtfab/openai-whisper-medium-transcription-and-summarization","mrolando/transcribe_audio","joaosanches/Brazilian-European_Portuguese","ashokrawat2023/hf-llm-api-dup","ClipHamper/openai-whisper-medium","willeasp/voice-chat-german","evertonaleixo/speech-to-speech-translation","iblfe/test","joseph-l-o/openai-whisper-medium","Liotax/steven"],"createdAt":"2022-09-26T06:52:52.000Z","safetensors":{"parameters":{"F32":763857920},"total":763857920},"usedStorage":22427556192}