关闭导航

包含标签" WER"的内容

MiniMax Speech-02登顶AI语音榜 零-shot克隆与Flow-VAE技术获突破
AI妹 1 个月前 7 0

In the rapidly developing field of artificial intelligence, the progress of domestic large models

CoGenAV音视频同步技术突破语音识别噪声干扰及多任务性能
AI妹 1 个月前 8 0

Recently, the Tongyi Foundation Model released CoGenAV, innovating voice recognition technology wi

NVIDIA Canary-Qwen-2.5B:ASR与LLM融合的顶尖开源商用混合模型
AI妹 1 个月前 8 0

NVIDIA has just released Canary-Qwen-2.5B, a groundbreaking hybrid model combining automatic speec