sherpa-onnx
sherpa-onnx copied to clipboard
k2-fsa
Speech-to-text, text-to-speech, speaker diarization, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V,...
i can gradle successfully this project, but when i run this app , app will crash The logcat are: ``` --------- beginning of main --------- beginning of kernel --------- beginning...
I have encountered an issue with the word **PRECENT** not being recognized. I attempted to generate a BPE for this word using the tool sherpa-onnx/scripts/text2token.py, which provided only one variant:...
Hybrid model * en-ru > Hello, I will Russian. Привет, я буду русский. > Привет I am sherpa-onnx * zh-en > Hello 我在 China > 我会中文 I understand Chinese 1....
streaming-hlg-decode-file-c-api.c调用sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13模型进行语音识别时，在不使用HLG的情况下，每次重新启动时都会出现第一个字不能识别（且不会自动换行）。
Otherwise, it is easy to miss the first word of a new segment.
Hi, would like to know if it is possible to modify the code to enable batch processing of the extraction of speaker embeddings?
We have already supported spoken language identification and audio tagging in our C APIs https://github.com/k2-fsa/sherpa-onnx/blob/bcd9e48150d8bcaf67b10d681615ba039255c776/sherpa-onnx/c-api/c-api.h#L874-L877 https://github.com/k2-fsa/sherpa-onnx/blob/bcd9e48150d8bcaf67b10d681615ba039255c776/sherpa-onnx/c-api/c-api.h#L1093-L01095 It would be great if someone can help support spoken launage identification and audio...
新手容易遇到的错误 首先感谢大佬 fangjun 1.首先，不要对代码进行任何修改， 编译 sherpa-ncnn。使用cmake，如果没有的话可以先装一个。 2.打开mfc下的sln进行编译 3.如果提示ms8041.这个是缺少对应的mfc导致的，经过上网，装了一堆vs2019的兼容，其实是不需要的，需要的是 a.C++ MFC for latest v143 build tools (x86 & x64) b.C++ MFC for latest v143 build tools (x86..... c.C++ Modules for v143...
 能否提供openharmony对应的onnxruntime 32位和64位的库
