![[Detailed Paper Reading] Zipformer: A faster and better encoder for automatic speech recognition](/media/video/2024/02/detailed-paper-reading-zipformer-a-faster-and-better-encoder-for-automatic-speech/preview.jpg)
Tutorials
[详细论文解读] Zipformer：自动语音识别的更快更优编码器
Conformer多年来一直是默认的ASR编码器，但k2/icefall团队的Zipformer在LibriSpeech、Aishell-1和WenetSpeech上悄悄夺得WER冠军，同时更快更轻。
![[Olewave's Long Review] Xception: Deep Learning with Depthwise Separable Convolutions](/media/video/2022/07/olewaves-long-review-xception-deep-learning-with-depthwise-separable-convolutions/preview.jpg)
Tutorials
[Olewave长评] Xception: 具有深度可分卷积的深度学习
Xception将Inception假设推向了逻辑极端,通过将跨通道和空间相关性分解为完全独立的操作,而它推广的深度可分卷积现在随处可见
![[Olewave's Short Review] Xception: Deep Learning with Depthwise Separable Convolutions](/media/video/2022/07/olewaves-short-review-xception-deep-learning-with-depthwise-separable-convolutions/preview.jpg)