# Transcription en français, édition du 9 novembre 2026

Tableau repris tel que Open ASR Leaderboard le publie : taux d'erreur par mot en français, moyenne de trois jeux de parole lue (FLEURS, Common Voice, MLS), plus bas est meilleur. Aucun score de QUELLE IA, aucun score combiné. Édition du 9 novembre 2026, relevé repris du 19 octobre 2026.

| Rang | Modèle | Éditeur | Valeur (%) |
| ---: | --- | --- | --- |
| 1 | [Azure LLM Speech 07 2026](https://quelleia.com/voix/modeles/microsoft-azure-speech-07-2026/) | Microsoft | 3,14 |
| 2 | [Azure Speech (06-2026)](https://quelleia.com/voix/modeles/microsoft-azure-speech-06-2026/) | Microsoft | 3,27 |
| 3 | [Scribe v2](https://quelleia.com/voix/modeles/scribe-v2/) | ElevenLabs | 3,29 |
| 4 | [Hojo-ASR-Multi-V1](https://quelleia.com/voix/modeles/hojo-asr-multi-v1/) | HojoAi | 3,57 |
| 5 | [Universal-3 Pro](https://quelleia.com/voix/modeles/universal-3-pro/) | AssemblyAI | 3,82 |
| 6 | [Symphony](https://quelleia.com/voix/modeles/sprag-symphony/) | Sprag | 3,92 |
| 6 | [Universal-3.5 Pro](https://quelleia.com/voix/modeles/assemblyai-universal-3-5-pro/) | AssemblyAI | 3,92 |
| 8 | [Cohere Transcribe](https://quelleia.com/voix/modeles/cohere-transcribe/) | Cohere | 4,02 |
| 9 | [Resonant-1](https://quelleia.com/voix/modeles/resonant-1/) | Reson8 | 4,11 |
| 9 | [Resonant-1-flash](https://quelleia.com/voix/modeles/resonant-1-flash/) | Reson8 | 4,11 |
| 9 | [Voxtral Small](https://quelleia.com/voix/modeles/voxtral-small/) | Mistral AI | 4,11 |
| 12 | [Multilingual Fast Transcription](https://quelleia.com/voix/modeles/modulate-multilingual/) | Modulate | 4,14 |
| 13 | [TheWhisper-Large-V3-Turbo](https://quelleia.com/voix/modeles/thestageai-thewhisper-large-v3-turbo/) | TheStage AI | 4,41 |
| 14 | [Canary 1B v2](https://quelleia.com/voix/modeles/nvidia-canary-1b-v2/) | NVIDIA | 4,79 |
| 15 | [GPT Transcribe](https://quelleia.com/voix/modeles/gpt-transcribe/) | OpenAI | 4,82 |
| 16 | [Speechmatics Enhanced](https://quelleia.com/voix/modeles/speechmatics-enhanced/) | Speechmatics | 4,89 |
| 17 | [Phi-4-multimodal-instruct](https://quelleia.com/voix/modeles/microsoft-phi-4-multimodal-instruct/) | Microsoft | 5,04 |
| 18 | [omniASR-LLM-7B-v2](https://quelleia.com/voix/modeles/meta-omniasr-llm-7b-v2/) | Meta | 5,25 |
| 19 | [Parakeet TDT 0.6B V3](https://quelleia.com/voix/modeles/nvidia-parakeet-tdt-0-6b-v3/) | NVIDIA | 5,30 |
| 20 | [Granite-Speech-4.1-2B-NAR](https://quelleia.com/voix/modeles/ibm-granite-speech-4-1-2b-nar/) | IBM | 5,40 |
| 21 | [Qwen3-ASR-1.7B-hf](https://quelleia.com/voix/modeles/alibaba-qwen3-asr-1-7b-hf/) | Alibaba | 5,68 |
| 22 | [Voxtral Mini](https://quelleia.com/voix/modeles/voxtral-mini/) | Mistral AI | 5,96 |
| 23 | [Soniox v5 Async](https://quelleia.com/voix/modeles/soniox-v5-async/) | Soniox | 6,21 |
| 24 | [Whisper Large v3](https://quelleia.com/voix/modeles/whisper-large-v3/) | OpenAI | 6,24 |
| 25 | [Whisper Large v3 Turbo](https://quelleia.com/voix/modeles/whisper-large-v3-turbo/) | OpenAI | 6,73 |
| 26 | [Muse Voice Transcribe](https://quelleia.com/voix/modeles/meta-muse-voice-transcribe/) | Meta | 6,81 |
| 27 | [omniASR-LLM-3B-v2](https://quelleia.com/voix/modeles/meta-omniasr-llm-3b-v2/) | Meta | 6,92 |
| 28 | [omniASR-LLM-1B-v2](https://quelleia.com/voix/modeles/meta-omniasr-llm-1b-v2/) | Meta | 7,00 |
| 29 | [omniASR-CTC-7B-v2](https://quelleia.com/voix/modeles/meta-omniasr-ctc-7b-v2/) | Meta | 7,57 |
| 30 | [Voxtral Mini 4B Realtime](https://quelleia.com/voix/modeles/voxtral-mini-4b-realtime/) | Mistral AI | 7,78 |
| 31 | [omniASR-CTC-3B-v2](https://quelleia.com/voix/modeles/meta-omniasr-ctc-3b-v2/) | Meta | 8,12 |
| 32 | [Qwen3-ASR-0.6B-hf](https://quelleia.com/voix/modeles/alibaba-qwen3-asr-0-6b-hf/) | Alibaba | 8,76 |
| 33 | [Nemotron 3.5 ASR](https://quelleia.com/voix/modeles/nvidia-nemotron-3-5-asr-streaming-0-6b/) | NVIDIA | 9,40 |
| 34 | [omniASR-LLM-300M-v2](https://quelleia.com/voix/modeles/meta-omniasr-llm-300m-v2/) | Meta | 10,02 |
| 35 | [omniASR-CTC-1B-v2](https://quelleia.com/voix/modeles/meta-omniasr-ctc-1b-v2/) | Meta | 10,29 |
| 36 | [Gemma 4 E4B](https://quelleia.com/voix/modeles/google-gemma-4-e4b-it/) | Google | 10,31 |
| 37 | [MOSS-Transcribe-Diarize](https://quelleia.com/voix/modeles/openmoss-team-moss-transcribe-diarize/) | OpenMOSS | 10,66 |
| 38 | [VibeVoice-ASR-HF](https://quelleia.com/voix/modeles/microsoft-vibevoice-asr-hf/) | Microsoft | 14,04 |
| 39 | [omniASR-CTC-300M-v2](https://quelleia.com/voix/modeles/meta-omniasr-ctc-300m-v2/) | Meta | 18,59 |

- Source : Open ASR Leaderboard, Hugging Face : https://huggingface.co/spaces/hf-audio/open_asr_leaderboard (relevé du 19 octobre 2026)

Source : QUELLE IA, édition du 9 novembre 2026, quelleia.com, d'après Open ASR Leaderboard.