Closed MoYiha closed 2 months ago
please post all of the logs.
---------------------------- PROCESS STARTED (9131) for package com.k2fsa.sherpa.onnx ----------------------------
2024-08-04 18:30:06.322 9131-9131 sherpa-onnx com.k2fsa.sherpa.onnx I Start to initialize model
2024-08-04 18:30:06.322 9131-9131 sherpa-onnx com.k2fsa.sherpa.onnx I Select VAD model type 0
2024-08-04 18:30:06.357 9131-9131 sherpa-onnx com.k2fsa.sherpa.onnx W config:
VadModelConfig(silero_vad=SilerVadModelConfig(model="silero_vad.onnx", threshold=0.5, min_silence_duration=0.25, min_speech_duration=0.25, window_size=512), sample_rate=16000, num_threads=1, provider="cpu", debug=False)
2024-08-04 18:30:06.470 9131-9131 libc com.k2fsa.sherpa.onnx E Access denied finding property "ro.hardware.chipname"
2024-08-04 18:30:06.681 9131-9131 sherpa-onnx com.k2fsa.sherpa.onnx I Finished initializing model
2024-08-04 18:30:06.681 9131-9131 sherpa-onnx com.k2fsa.sherpa.onnx I Start to initialize non-streaimng recognizer
2024-08-04 18:30:06.681 9131-9131 sherpa-onnx com.k2fsa.sherpa.onnx I Select model type 15 for ASR
2024-08-04 18:30:06.684 9131-9131 sherpa-onnx com.k2fsa.sherpa.onnx W config:
OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="en", task="transcribe", tail_paddings=1000), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model=""), sense_voice=OfflineSenseVoiceModelConfig(model="sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17/model.int8.onnx", language="en", use_itn=True), telespeech_ctc="", tokens="sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5), ctc_fst
2024-08-04 18:30:16.345 9131-9131 sherpa-onnx com.k2fsa.sherpa.onnx I Finished initializing non-streaming recognizer
2024-08-04 18:30:16.465 9131-9131 sherpa-onnx com.k2fsa.sherpa.onnx I Audio record is permitted
2024-08-04 18:30:16.523 9131-9154 AdrenoGLES-0 com.k2fsa.sherpa.onnx I QUALCOMM build : 781e7d0, I46ff5fc46f
Build Date : 12/01/20
OpenGL ES Shader Compiler Version: EV031.31.04.01
Local Branch : QPR1
Remote Branch :
Remote Branch :
Reconstruct Branch :
2024-08-04 18:30:16.523 9131-9154 AdrenoGLES-0 com.k2fsa.sherpa.onnx I Build Config : C P 11.0.1 AArch64
2024-08-04 18:30:16.523 9131-9154 AdrenoGLES-0 com.k2fsa.sherpa.onnx I Driver Path : /vendor/lib64/egl/libGLESv2_adreno.so
2024-08-04 18:30:16.575 9131-9154 AdrenoGLES-0 com.k2fsa.sherpa.onnx I PFP: 0x016ee189, ME: 0x00000000
2024-08-04 18:30:16.582 9131-9154 AdrenoUtils com.k2fsa.sherpa.onnx W
Fixed in #1214
Please try the latest master.
Log: STDOUT: /home/runner/work/sherpa-onnx/sherpa-onnx/sherpa-onnx/csrc/offline-recognizer-sense-voice-impl.h:DecodeOneStream:260 Unknown language: en. Use 0 instead.
https://github.com/k2-fsa/sherpa-onnx/blob/d5f486878d895ece13a0673e383fc8f69dfcd5d1/sherpa-onnx/csrc/offline-sense-voice-model.cc#L102-L105