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'm looking to use some of the pretrained speech recognizers and compute their encoder output features in real-time. When I'm looking at the API of _Recognizer / _sherpa_onnx.OnlineRecognizer as defined...
I've downloaded the necessary models and configured the path for the 2pass example. I get this error in logcat: `Read binary file: Load /data/user/0/com.k2fsa.sherpa.onnx/files/sherpa-onnx-streaming-zipformer-en-2023-06-26/encoder-epoch-99-avg-1-chunk-16-left-128.int8.onnx failed` Where should I copy the...
reproduce: ``` wget https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-streaming-paraformer-bilingual-zh-en.tar.bz2 tar xvf sherpa-onnx-streaming-paraformer-bilingual-zh-en.tar.bz2 ./bin/sherpa-onnx \ --provider=coreml \ --tokens=./sherpa-onnx-streaming-paraformer-bilingual-zh-en/tokens.txt \ --paraformer-encoder=./sherpa-onnx-streaming-paraformer-bilingual-zh-en/encoder.onnx \ --paraformer-decoder=./sherpa-onnx-streaming-paraformer-bilingual-zh-en/decoder.onnx \ ./sherpa-onnx-streaming-paraformer-bilingual-zh-en/test_wavs/0.wav OnlineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0), model_config=OnlineModelConfig(transducer=OnlineTransducerModelConfig(encoder="", decoder="", joiner=""), paraformer=OnlineParaformerModelConfig(encoder="./sherpa-onnx-streaming-paraformer-bilingual-zh-en/encoder.onnx", decoder="./sherpa-onnx-streaming-paraformer-bilingual-zh-en/decoder.onnx"), wenet_ctc=OnlineWenetCtcModelConfig(model="", chunk_size=16,...
java.lang.UnsatisfiedLinkError: dlopen failed: could not load library "libsherpa-onnx-core.so" needed by "libsherpa-onnx-jni.so"; caused by could not load library "libkaldi-native-fbank-core.so" needed by "libsherpa-onnx-core.so"; caused by cannot locate symbol "rand_r" referenced by "libkaldi-native-fbank-core.so"...
https://github.com/myshell-ai/MeloTTS I tried to modify the `export-onnx-ljs.py` script, I got as far as the `get_text`. MeloTTS returns tones as well as phonemes, is this easy to support in sherpa-onnx?
I've been always trying to use Sherpa to implement syllable-level speech recognition (1.use a few pinyins to detect hotword directly; 2.or send a long sequence of pinyins to a LLM(gpt...
