Unverified50% confidenceFactExact time
MOSS-Transcribe-Diarize 的解码器采用 Qwen3-0.6B 风格的解码器
1
Sources
50%
Confidence
Long-term
Relevance
7/11/2026
First Seen
Sources
MOSS-Transcribe-Diarize：0.9B端到端多说话人语音转写模型
twitterlmsysorg7/9/2026
Related Claims
UnverifiedQQ Music's QRC format supports word-level timestamps and uses zlib compression and simple encryption.63% similarVerifiedWhisper's architecture adopts an encoder-decoder structure, where the encoder transforms the mel spectrogram of audio into high-dimensional feature representations, and the decoder generates text output word by word in an autoregressive manner.61% similarUnverifiedMOSS-Transcribe-Diarize 将转写与说话人分离两大任务合二为一，用单一模型完成，直接输出带有时间戳和说话人标签的结构化文本60% similarUnverifiedQwen-Image 3.0支持最长4.5K Token的指令输入，支持10px级别文本渲染和12种语言原生排版60% similarUnverified多级编解码级联（tandem coding）会引入累积失真，经过三次以上编解码级联的音频其频谱失真模式已超出简单编解码器模拟所能覆盖的范围59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/486958API
curl https://kongchang.com/api/v1/knowledge/claims/486958MCP
get_claim(id=486958)