←Search results

Search “Speech”

By relevance · Total 210 results Clear search

Wednesday

  1. TechCrunch AI

    Nvidia Releases Open Source Transcription Model Nemotron 3.5 Transcribe

    Nvidia has released the free open-weight model Nemotron 3.5 Transcribe, which can transcribe audio in up to 40 languages, and simultaneously launched version 2 of the open speech dataset Granary. The model supports translation between 31 languages and English, processes recordings up to one hour long, and distinguishes up to 8 speakers; Nvidia claims it outperforms competing products on benchmarks such as the Hugging Face Open ASR Leaderboard. The model has 30 billion parameters and can run on Jetson AGX Thor, DGX Spark, and Blackwell data center chips, but it only supports recorded audio and does not support live streams.

    Nvidia has released the free open-weight model Nemotron 3.5 Transcribe, which can transcribe audio in up to 40 languages, and simultaneously launched version 2 of the open speech dataset Granary. The model supports translation between 31 languages and English, processes recordings up to one hour long, and distinguishes up to 8 speakers; Nvidia claims it outperforms competing products on benchmarks such as the Hugging Face Open ASR Leaderboard. The model has 30 billion parameters and can run on J

    Matched fieldsSummary、Body

    #tech-media#Model releases#Speech#Open-source ecosystem

Wednesday

  1. Matt Turck

    Gradium open-sources the Phonon on-device TTS model suite, with all models under 50m parameters

    Gradium open-sources the Phonon on-device speech synthesis model suite, with all models under 50m parameters, focused on multilingual naturalness and accuracy, and claims to offer the broadest inference support to date. Phonon-31m is released under the Apache 2.0 license. Matt Turck reposted this news.

    Matched fieldsSummary、Body

    #ai-news#Model releases#Speech#English text is being prepared.

Tuesday

  1. Ant Group's inclusionAI: New GitHub repository

    Ant Group's inclusionAI open-sources the Ming-3.0-audio-flash native audio model

    Ant Group's inclusionAI has open-sourced the Ming-3.0-audio-flash native audio model on GitHub. It uses a 126B-parameter MoE architecture with 6.5B activated parameters, and there is also a Ming-3.0-audio-tiny version with 9.3B parameters and 2.7B activated parameters. The models cover Chinese and English recognition across multiple dialects and accents, long audio understanding, audio reasoning, and end-to-end speech dialogue. They support three inference methods: vLLM-Omni, SGLang, and Transformers, and are released under the MIT license.

    License: MIT

    Ant Group's inclusionAI has open-sourced the Ming-3.0-audio-flash native audio model on GitHub. It uses a 126B-parameter MoE architecture with 6.5B activated parameters, and there is also a Ming-3.0-audio-tiny version with 9.3B parameters and 2.7B activated parameters. The models cover Chinese and English recognition across multiple dialects and accents, long audio understanding, audio reasoning, and end-to-end speech dialogue. They support three inference methods: vLLM-Omni, SGLang, and Transfo

    Matched fieldsSummary、Body

    #engineering#Model releases#Open-source ecosystem#Speech

Monday

Friday

Thursday

Wednesday

Tuesday

Saturday

Thursday

Tuesday

Wednesday

Saturday

  1. Tongyi Qianwen / QwenSelected

    Qwen Releases Real-Time Simultaneous Interpretation Model Qwen3.8-LiveTranslate

    Qwen has released its next-generation real-time simultaneous interpretation model, Qwen3.8-LiveTranslate, built on the Interleave architecture. Across 60 languages, it reduces average latency (LAAL) from 2.8s to 2.3s, while improving faithfulness, fluency, and conciseness. New capabilities include real-time speaker diarization, which can distinguish speakers in multi-party speech and preserve each person's voice through more stable voice cloning; synchronized bilingual display, presenting the source text and translation on the same screen; and long-context disambiguation, which uses conversation history to clarify names and terminology to ensure translation consistency. The model is now available on QwenCloud, and the official release also provides links to a blog post and case studies.

    Qwen has released its next-generation real-time simultaneous interpretation model, Qwen3.8-LiveTranslate, built on the Interleave architecture. Across 60 languages, it reduces average latency (LAAL) from 2.8s to 2.3s, while improving faithfulness, fluency, and conciseness. New capabilities include real-time speaker diarization, which can distinguish speakers in multi-party speech and preserve each person's voice through more stable voice cloning; synchronized bilingual display, presenting the so

    Matched fieldsSummary

    #company#Model releases#Speech#Multimodal

Wednesday