{"id":"alibaba-qwen3-asr-1-7b-hf","nom":"Qwen3-ASR-1.7B-hf","editeur":"Alibaba","pays":"Chine","poids_ouverts":true,"poids_selon":null,"licence":"Apache 2.0","licence_selon":null,"liens":{"page":"https://huggingface.co/Qwen/Qwen3-ASR-1.7B-hf","essayer":"https://huggingface.co/spaces/Qwen/Qwen3-ASR"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/alibaba-qwen3-asr-1-7b-hf/","releve":"2026-10-19","en_bref":"21e sur 39 en transcription en français ; 9e sur 53 en transcription en anglais (Open ASR).","presentation":"Carte Qwen3-ASR au format natif Transformers publiée par Alibaba (Qwen), pour la transcription avec identification de la langue sur 30 langues et 22 dialectes chinois, hors ligne ou en streaming, y compris le chant et les chansons avec accompagnement. Alibaba présente la taille 1.7B comme la plus précise de la famille et la compare aux API commerciales de transcription.","sortie":"2026-06-26","langues":{"annoncees":{"annoncees":"30 langues et 22 dialectes chinois, dont le français","nombre":30,"francais":true,"liste":["zh","en","yue","ar","de","fr","es","pt","id","it","ko","ru","th","vi","ja","tr","hi","ms","nl","sv","da","fi","pl","cs","fil","fa","el","hu","mk","ro"]},"prises_en_charge_selon_open_tts":null,"evaluees":["fr","en"]},"preuves":[{"appuie":["presentation"],"lu":"https://huggingface.co/Qwen/Qwen3-ASR-1.7B-hf/raw/main/README.md (« Qwen3-ASR (Transformers native) »), 17/10/2026"},{"appuie":["langues","presentation"],"lu":"https://huggingface.co/Qwen/Qwen3-ASR-1.7B-hf/raw/main/README.md (« Supports language identification and speech recognition for 30 languages and 22 Chinese dialects »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://huggingface.co/Qwen/Qwen3-ASR-1.7B-hf/raw/main/README.md (« The 1.7B version achieves state-of-the-art performance among open-source ASR models and is competitive with the strongest proprietary commercial APIs. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://huggingface.co/Qwen/Qwen3-ASR-1.7B-hf/raw/main/README.md (« Offline / Streaming | Speech, Singing Voice, Songs with BGM »), 17/10/2026"},{"appuie":["langues"],"lu":"https://huggingface.co/Qwen/Qwen3-ASR-1.7B-hf/raw/main/README.md (« Chinese (zh), English (en), Cantonese (yue), Arabic (ar), German (de), French (fr), Spanish (es) »), 17/10/2026"},{"appuie":["sortie"],"lu":"https://raw.githubusercontent.com/QwenLM/Qwen3-ASR/main/README.md (« 2026.6.26: 🤗🤗🤗 Native Transformers support is now available! It includes `torch.compile` support for faster inference. See the new model cards for example usage »), 17/10/2026"}],"classements":[{"id":"transcription/francais","nom":"Transcription en français","rang":21,"sur":39,"valeur":5.68,"unite":"%","chiffres":{"rtfx":378.72,"jeux":{"Common Voice":7.84,"FLEURS":4.06,"MLS":5.15}},"voisins":["ibm-granite-speech-4-1-2b-nar","voxtral-mini"],"source":{"nom":"Open ASR Leaderboard","mention":"Source : Open ASR Leaderboard, Hugging Face","url":"https://huggingface.co/spaces/hf-audio/open_asr_leaderboard","releve":"2026-10-19"}},{"id":"transcription/open-asr-anglais","nom":"Transcription en anglais, Open ASR","rang":9,"sur":53,"valeur":5.4,"unite":"%","chiffres":{"rtfx":819.3,"jeux":{"AMI-Cleaned":8.31,"Earnings22-Cleaned-AA-chunked":5.84,"Gigaspeech-Cleaned":7.22,"LS Clean":1.26,"LS Other":2.94,"Private (conversational)":12.14,"Private (scripted)":2.87,"SPGISpeech":2.57,"URGENT24":9.93,"Voice Arena Monsoon":3.5,"Voxpopuli-AA-Cleaned":2.85}},"voisins":["assemblyai-universal-3-5-pro","smallest-ai-pulse"],"source":{"nom":"Open ASR Leaderboard","mention":"Source : Open ASR Leaderboard, Hugging Face","url":"https://huggingface.co/spaces/hf-audio/open_asr_leaderboard","releve":"2026-10-19"}}],"noms_dans_les_sources":{"hf_audio":"Qwen/Qwen3-ASR-1.7B-hf"}}