{"_id":"63314bb6acb6472115aa55a9","id":"openai/whisper-tiny","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":1590627,"likes":442,"modelId":"openai/whisper-tiny","author":"openai","sha":"169d4a4341b33bc18d8881c4b69c2e104e1cc0af","lastModified":"2024-02-29T10:57:33.000Z","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-tiny","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":7.54,"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":17.15,"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":141,"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-tiny","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":7.54,"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":17.15,"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":141,"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","treble-technologies/ffasr","eduagarcia/multilingual-tokenizer-leaderboard","VIDraft/Portrait-Animation","Ailyth/Multi-voice-TTS-GPT-SoVITS","sanchit-gandhi/whisper-jax-spaces","OpenSound/CapSpeech-TTS","Matthijs/whisper_word_timestamps","radames/whisper-word-level-trim","lmz/candle-whisper","gobeldan/insanely-fast-whisper-webui","devilent2/whisper-v3-zero","kadirnar/Whisper_M2M100_BioGpt","speechbox/whisper-speaker-diarization","nvidia/audio-flamingo-2","Splend1dchan/BreezyVoice-Playground","GenAISecurityProject/OWASP-AIBOM-Generator","ardha27/Youtube-AI-Summarizer","souljoy/ChatPDF","mozilla-ai/transcribe","JacobLinCool/BreezyVoice","RyeAI/danish-asr-leaderboard","innev/whisper-Base","abidlabs/hfstudio","hchcsuim/Automatic-Speech-Recognition-Speech-to-Text","joaogante/assisted_generation_benchmarks","eustlb/whisper-vs-distil-whisper-fr","ghostai1/Audio-Translator","CeibalUY/transcribir_audio","RaviNaik/MultiModal-Phi2","TaiYouWeb/whisper-multi-model","yagmurtuncer/turkish-asr-leaderboard","kevinwang676/GPT-SoVITS-Trilingual","devilent2/whisper-v3-zero-dev","ardha27/VideoAnalyzer","Anupam007/Automated-Meeting-Minutes","ranialahassn/languagedetectorWhisper","Johnyquest7/medical-transcription-notes","banao-tech/musetalk-avatar","build-small-hackathon/ai-avatar-assistant","renatotn7/editarVideoAtravesDeTexto","radames/candle-whisper","vakodiya/streamlit-gpt2","sampsontan/llama3-rag","seepine/Multi-voice-TTS-GPT-SoVITS","invincible-jha/MentalHealthVocalBiomarkers","lele1894/dubbing","Ericboi229-gmx-co-uk/insanely-fast-whisper-webui","Hamam12/Hoama","yolloo/VoiceQ","sk61tc4j53obiq/lipsmusemodel","qwvdggg/newtryEsp","Speedofmastery/orynxml-backend","Piyush1225/talkmateai-backend","Yash030/claude-code-proxy","build-small-hackathon/TrailHead","ArtFix0/speech-to-speech-dashboard","renatotn7/EspacoTeste","IstvanPeter/openai-whisper-tiny","joaogabriellima/openai-whisper-tiny","abrar-adnan/speech-analyzer","ahmedghani/Inference-Endpoint-Deployment","GiorgiSekhniashvili/geo-whisper","reach-vb/whisper_word_timestamps","jamesyoung999/whisper_word_timestamps","OdiaGenAI/Olive_Whisper_ASR","Aryan619348/google-calendar-agent","seiching/ainotes","filben/transcrever_audio_pt","Tonic/WhisperFusionTest","sdlc/Multi-Voice","ricardo-lsantos/openai-whisper-tiny","Tohidichi/Semantic-chunker-yt-vid","devilent2/whisper-v3-zero-canary","MikeTangoEcho/asrnersbx","GatinhoEducado/speech-to-speech-translation","RenanOF/AudioTexto","Anupam251272/Real-Time-Language-Translator-AI","garyd1/AI_Mock_Interview","Jwrockon/ArtemisAIWhisper","ZealAI/Zeal-AI","abdullahbilal-y/ML_Playground_Dashboard","Anupam007/RealTime-Meeting-Notes","chakchakAI/CrossTalk-Translation-AI","AhmedKElsayed/NonToxicMe","GMI-AI/Speech-Processing-Lab-Project-App","anushka027/Whispr.ai","Draxgabe/acuspeak-demo","sebibibaba/Transcripteur-Vocal","pareek-voicearena/test-hindi-2","amurienne/sambot","dwitee/ai-powered-symptom-triage","KNipun/Whisper-AI-Psychiatric","notojasv/voice-assistant-demo","PoojaDinesh99/breath-easy-thesis","Oscargad/twi-chinese-translator","JeovaniPB/AIBORA-VOICE-AI","Esurupooja/Voice_Bot","shushukimura/whisper-asr-space","PatienceIzere/AudioTranscriber"],"createdAt":"2022-09-26T06:50:30.000Z","safetensors":{"parameters":{"F32":37760640},"total":37760640},"usedStorage":1831289730}