sherpa-onnx
sherpa-onnx copied to clipboard
k2-fsa
Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android...
Is there any possibility to get start and end timestamp both for every token, currently we are getting only start time of every token. A scenario that we face in...
In recent iOS updates, Apple now allows for any speech synthesizers brought into iOS via an App to become a part of the custom options for the iOS system voices...
我想使用这个预训练模型：https://k2-fsa.github.io/sherpa/onnx/kws/pretrained_models/index.html 我想知道我应该怎么配置keywords.txt文件 我修改了配置，对应我的模型文件 我不知道我该在哪里配置 我尝试在hotwordsFile里配置 但是报错： 我想知道怎么在ios端使用关键词的模型呢 非常感谢
Here is the error message: ``` ---vits model--- sample_rate=22050 has_espeak=1 comment=piper n_speakers=1 voice=en-us language=English model_type=vits ----------input names---------- 0 input 1 input_lengths 2 scales ----------output names---------- 0 output 2024-06-02 18:58:52.961 16536-17804...
Hi, I cannot select the downloaded engine in the Android settings, because it crashes every time. I've already read #528, but it doesn't matter if the app is closed or...
Tested with the example SherpaOnnxTTS android application. To reproduce: 1. Build android arm64_v8a (with onnx 1.18, using https://github.com/csukuangfj/onnxruntime-libs/releases/tag/v1.18.0) 2. Copy built JNI into the example tts project 3. Run app...
运行环境： cpu：CortexA53 model：vits-icefall-zh-aishell3.tar.bz2 硬件环境：aarch64 我不知道是否有设置或者加速手段解决这个问题，谢谢
Observing some mismatched outputs with sherpa-onnx tensorrt backend with concurrent calls. Or this would be my own internal issue, still debugging, just keeping a note! cc: https://github.com/microsoft/onnxruntime/issues/19275
