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...
Hello, development team! At the moment, I’m experimenting with giga-rnnt-v2, focusing on parallel inference of the model. What has been done so far: 0. The model sherpa-onnx-nemo-transducer-giga-am-v2-russian-2025-04-19.tar.bz2 was downloaded from...
This PR adds LODR support from Icefall to offline and online recognizers for both LM shallow fusion and LM rescore. (see https://k2-fsa.github.io/icefall/decoding-with-langugage-models/LODR.html) Usage example: ``` # offline LM rescore sherpa-onnx-offline...
hello The canary-180m is ranked 9th in the https://huggingface.co/spaces/hf-audio/open_asr_leaderboard ASR ranking. With a size of only 700MB and very good transcription accuracy, it is very suitable for local transcription. Is...
why all the english related model in asr cannot recognize well? though Chinese ones seem work well. Have you tested the english related models? Am i missing anything to make...
Hi In the Arabic context, short vowels are not written directly. So e-speak is not capable of reading correctly. There has been a great amount of research for models inheriting...
您好，我在使用sherpa-onnx-offline-tts-play进行tts推理时出现，能否帮忙看看是什么原因？谢谢。 下面是运行的打印信息： ./sherpa-onnx-offline-tts-play --vits-model=./vits-melo-tts-zh_en/model.onnx --vits-lexicon=./vits-melo-tts-zh_en/lexicon.txt --vits-tokens=./vits-melo-tts-zh_en/tokens.txt --tts-rule-fsts="./vits-melo-tts-zh_en/date.fst,./vits-melo-tts-zh_en/number.fst" --vits-dict-dir=./vits-melo-tts-zh_en/dict --provider="cuda" --output-filename=../zh-en-2.wav "测试tts样例，1000识别，" /home/ubuntu/work/git_program/deeplearning/text-to-speech/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:375 .//sherpa-onnx-offline-tts-play --vits-model=./vits-melo-tts-zh_en/model.onnx --vits-lexicon=./vits-melo-tts-zh_en/lexicon.txt --vits-tokens=./vits-melo-tts-zh_en/tokens.txt --tts-rule-fsts=./vits-melo-tts-zh_en/date.fst,./vits-melo-tts-zh_en/number.fst --vits-dict-dir=./vits-melo-tts-zh_en/dict --provider=cuda --output-filename=../zh-en-2.wav '测试tts样例，1000识别，' ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.rear ALSA lib pcm.c:2495:(snd_pcm_open_noupdate)...
网页上rule-66.wav的发声很清楚。 我编译后用相同的指令得到的声音很奇怪。 网页上rule-66.wav的发声是怎么实现的
