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...
I got this error generating TTS audio with provider = "coreml" ``` 2025-02-04 22:24:47.002908 [I:onnxruntime:, model_builder.cc:926 SaveModel] Writing CoreML Model to /private/var/mobile/Containers/Data/Application/9F1EE4F3-7EC8-4572-A177-A6237E1E8E2F/tmp/onnxruntime-9F750DCD-7DEF-46C5-991E-2E7CC3663DA4-29393-00001A50FC386A09.model.mlmodel libc++abi: terminating due to uncaught exception of type...
1、这个是日志 FATAL EXCEPTION: textTranslation Process: com.example.aartest, PID: 13235 java.lang.NoClassDefFoundError: Failed resolution of: Lai/onnxruntime/OrtEnvironment; at android.yan.kernel.translate.Translator$1.run(Translator.java:98) Caused by: java.lang.ClassNotFoundException: Didn't find class "ai.onnxruntime.OrtEnvironment" on path: DexPathList[[zip file "/data/app/~~JCTw255ZQ2sW71_agJPkQA==/com.example.aartest-cGT4KKr4Z9wQMCGedTZ5FQ==/base.apk"],nativeLibraryDirectories=[/data/app/~~JCTw255ZQ2sW71_agJPkQA==/com.example.aartest-cGT4KKr4Z9wQMCGedTZ5FQ==/lib/arm64, /data/app/~~JCTw255ZQ2sW71_agJPkQA==/com.example.aartest-cGT4KKr4Z9wQMCGedTZ5FQ==/base.apk!/lib/arm64-v8a, /system/lib64, /system_ext/lib64]]...
使用TTS默认参数, 模型使用 csukuangfj/sherpa-onnx-vits-zh-ll (Chinese, 5 speakers)[](https://k2-fsa.github.io/sherpa/onnx/tts/pretrained_models/vits.html#csukuangfj-sherpa-onnx-vits-zh-ll-chinese-5-speakers) 同样的sid , 自己跑生成的语音文件 时常5秒,样例中的是8秒, 仔细听下来在断句处都没有停顿 [自己生成](https://github.com/bsdgo/tts/raw/refs/heads/main/generate_wav.wav) [官网样例](https://k2-fsa.github.io/sherpa/_static/sherpa-onnx-vits-zh-ll/4-heteronym.wav)
It would be really nice if Sherpa-Onnx could support native VisionOS Development with SwiftUI. At the moment, the current Sherpa-Onnx.xcframework does not contain the binaries to build a native app...
@pkufool 简单描述一下。我直接用的keyword-spotting-from-microphone这个demo 但是添加唤醒词 比如输入 带有“XX室” 或者“XX础" （目前只测出这两个字有问题） 的时候会报错 初始化的时候就错误了 代码如下： public class keyword_spotting_from_microphone { public keyword_spotting_from_microphone() { var config = new KeywordSpotterConfig(); config.FeatConfig.SampleRate = 16000; config.FeatConfig.FeatureDim = 80; config.ModelConfig.Transducer.Encoder =...
Hi, I’m using the following model configuration: ``` encoder:=../models/sherpa-onnx-streaming-zipformer-korean-2024-06-16/encoder-epoch-99-avg-1.int8.onnx \ decoder:=../models/sherpa-onnx-streaming-zipformer-korean-2024-06-16/decoder-epoch-99-avg-1.onnx \ decoding_method:=modified_beam_search \ joiner:=../models/sherpa-onnx-streaming-zipformer-korean-2024-06-16/joiner-epoch-99-avg-1.int8.onnx \ tokens:=../models/sherpa-onnx-streaming-zipformer-korean-2024-06-16/tokens.txt \ bpe_vocab:=../models/sherpa-onnx-streaming-zipformer-korean-2024-06-16/bpe.vocab \ hotwords_file:=../models/sherpa-onnx-streaming-zipformer-korean-2024-06-16/hotwords_ko.txt \ hotwords_score:=2.0 \ vad_model:=../models/silero_vad.onnx ``` I’ve followed the guide...
I've noticed that the **Hugging Face Kokoro-TTS** [hosted on Spaces](https://huggingface.co/spaces/hexgrad/Kokoro-TTS) handles phonemes exceptionally well, distinguishing between cases like: - "read" (past vs. present tense) - "a project" vs. "to project"...
Overall I try to speed up kokoro TTS inference using CoreML provider on iOS and I know onnxruntime improved a lot `CoreMLExecutionProvider` . I tried to update sherpa-onnx to use...
I have fine-tuned a Paraformer model, but the version is not 0.8.8. I tried to use version 0.8.8 to export ONNX, but it failed. Can you tell me your versions...
