sherpa-onnx icon indicating copy to clipboard operation
sherpa-onnx copied to clipboard

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,...

Results 224 sherpa-onnx issues
Sort by recently updated
recently updated
newest added

Hi Thanks for your awesome work! I tried the Arabic TTS voice (Kareem), and I noticed that an important text preprocessing step is missing. Arabic text is usually unvocalized (aka...

Is there a way to build the TTS WASM example in a way that it can be used in a Vite-based project? At the moment, a lot of paths/other stuff...

I had followed exact steps mentioned here: https://k2-fsa.github.io/sherpa/onnx/ios/build-sherpa-onnx-swift.html Please help to fix for OS 17.3 Thanks Here is the crash log, *** Terminating app due to uncaught exception 'com.apple.coreaudio.avfaudio', reason:...

Hello! I was trying to convert the latest FastConformer Model from Nvidia for use in Sherpa-onnx called 'STT En FastConformer Hybrid Transducer-CTC Large Streaming Multi' Model link: https://catalog.ngc.nvidia.com/orgs/nvidia/teams/nemo/models/stt_en_fastconformer_hybrid_large_streaming_multi I used...

Too many overruns. It is very likely that the RTF on your board is larger than 1. Please use ./bin/sherpa-onnx to compute the RTF

Is it possible to use Streaming transformer models in sherpa_onnx example model: [ speechcatcher/speechcatcher_german_espnet_streaming_transformer_13k_train_size_m_raw_de_bpe1024](https://huggingface.co/speechcatcher/speechcatcher_german_espnet_streaming_transformer_13k_train_size_m_raw_de_bpe1024)

Hi. I have a phoneme-based Zipformer model, and I have successfully integrated a HLG component which takes the phonemes and converts it to a sequence of words. I've tried the...

Desperately looking for TTS that can be used in Unity and built to Android that supports my native language. So far the Piper models are the only local TTS that...

Could this possible using ffi ? Ex : https://pub.dev/packages/onnxruntime