add batch processing to sherpa-onnx (k2-fsa#166) jingzhaooucommitted Verified fdd49d0 Commits on Jun 2, 2023 Added provider option to sherpa-onnx and decode-file-c-api (k2-fsa#162) jingzhaooucommitted Verified 0ed501b Commits on May 30, 2023 add streaming-server with web client (...
Update sherpa-onnx-tts.js VitsModelConfig.model can be none by @cgisky1980 in #1817 Fix passing gb2312 encoded strings to tts on Windows by @csukuangfj in #1819 Support scaling the duration of a pause in TTS. by @csukuangfj in #1820 Fix building wheels for linux aarch64. by @csu...
https://k2-fsa.github.io/sherpa/onnx/ios/build-sherpa-onnx-swift.html 可见sherpa的技术支持是比较全面的。 经过实验对比,使用Onnxruntime推理模型,资源消耗减少,并发量及解码速度有较大提升。 语音识别k2sherpakaldi 分享至 投诉或建议 1 0 1
k2-fsa.github.io/icefal 流式识别验证 命令如下: ./lstm_transducer_stateless2/streaming-ncnn-decode.py \ --bpe-model-filename ./data/lang_bpe_500/bpe.model \ --encoder-param-filename ./lstm_transducer_stateless2/exp/encoder_jit_trace-pnnx.ncnn.param \ --encoder-bin-filename ./lstm_...
kennedy-0.wavgithub.com/k2-fsa/next- armstrong-99.wav github.com/k2-fsa/next- 注:本文使用的模型为网上开源的预训练模型。 体验 我们提供三种方式供大家体验 sherpa-onnx 里的文字转语音。 Android APK 我们提供预编译的 Android APK 供大家下载。 语言APK 下载地址 中文 github.com/k2-fsa/sherp 英文 ...
$ git clone https://github.com/Tencent/ncnn.git $ cd {Your_Path}/ncnn/ $ mkdir -p build $ cd build $ cmake .. $ make -j4 1. 2. 3. 4. 5. 6. 转换操作: paddlepaddle->onnx AI检测代码解析 # 文本检测 $ paddle2onnx--model_dir {your_ocr_det_paddlepaddle_model_root_path} ...
sh-x./build-arm-linux-gnueabihf.sh 编译成功后, 3、下载模型库,参考: 代码语言:javascript 代码运行次数:0 运行 AI代码解释 使用的模型是小模型:https://k2-fsa.github.io/sherpa/ncnn/pretrained_models/zipformer-transucer-models.html#sherpa-ncnn-streaming-zipformer-small-bilingual-zh-en-2023-02-16...
为了简单,将/my/lib修改为777的权限,chmod 777 /my/lib -R ,否则执行sherpa-onnx-offline-tts会报Permission denied。 (2)、将sherpa-onnx-offline-tts也拷贝到开发板上。 5、下载模型,运行 wget https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/vits-icefall-zh-aishell3.tar.bz2 ...
"sherpa_onnx":"sherpa-onnx/python/sherpa_onnx", }, packages=["sherpa_onnx"], data_files=[("bin",get_binaries_to_install())], url="https://github.com/k2-fsa/sherpa-onnx", long_description=read_long_description(), long_description_content_type="text/markdown", ...
log"https://huggingface.co/csukuangfj/sherpa-onnx-streaming-zipformer-en-2023-06-26" # Download the model # see https://k2-fsa.github.io/sherpa/onnx/pretrained_models/online-transducer/zipformer-transducer-models.html#csukuangfj-sherpa-onnx-streaming-zipformer-en-2023-06-26-english ...