百度自动驾驶盈利 百度自动驾驶技术怎么样



文章插图
百度自动驾驶盈利 百度自动驾驶技术怎么样

文章插图
【百度自动驾驶盈利 百度自动驾驶技术怎么样】kaldi是功能齐全性能高效的语音识别开源项目 , 锐英源软件对kaldi有丰富经验 , 今天把以前处理过程中的一个错误分享给大家 , 能帮大家节省时间 。有个配置文件里参数错了 , 是和Mel无关的参数 , 改回原来值就可以了 。
LOG (online2-wav-nnet3-latgen-faster[5.5.839~8-0c6a]:ComputeDerivedVars():ivector-extractor.cc:183) Computing derived variables for iVector extractorLOG (online2-wav-nnet3-latgen-faster[5.5.839~8-0c6a]:ComputeDerivedVars():ivector-extractor.cc:204) Done.LOG (online2-wav-nnet3-latgen-faster[5.5.839~8-0c6a]:RemoveOrphanNodes():nnet-nnet.cc:948) Removed 1 orphan nodes.LOG (online2-wav-nnet3-latgen-faster[5.5.839~8-0c6a]:RemoveOrphanComponents():nnet-nnet.cc:847) Removing 2 orphan components.LOG (online2-wav-nnet3-latgen-faster[5.5.839~8-0c6a]:Collapse():nnet-utils.cc:1488) Added 1 components, removed 2LOG (online2-wav-nnet3-latgen-faster[5.5.839~8-0c6a]:CompileLooped():nnet-compile-looped.cc:345) Spent 0.0127561 seconds in looped compilation.ASSERTION_FAILED (online2-wav-nnet3-latgen-faster[5.5.839~8-0c6a]:MelBanks():mel-computations.cc:124) Assertion failed: (first_index != -1 && last_index >= first_index && “You may have set –num-mel-bins too large.”)[ Stack-Trace: ]/home/server/kaldi-trunk/src/lib/libkaldi-base.so(kaldi::MessageLogger::LogMessage() const+0xb42) [0x7f8a92744692]/home/server/kaldi-trunk/src/lib/libkaldi-base.so(kaldi::KaldiAssertFailure_(char const*, char const*, int, char const*)+0x6e) [0x7f8a9274538e]/home/server/kaldi-trunk/src/lib/libkaldi-feat.so(kaldi::MelBanks::MelBanks(kaldi::MelBanksOptions const&, kaldi::FrameExtractionOptions const&, float)+0x7bd) [0x7f8a92e44e09]/home/server/kaldi-trunk/src/lib/libkaldi-feat.so(kaldi::MfccComputer::GetMelBanks(float)+0x8a) [0x7f8a92e40886]/home/server/kaldi-trunk/src/lib/libkaldi-feat.so(kaldi::MfccComputer::MfccComputer(kaldi::MfccOptions const&)+0x3ea) [0x7f8a92e41036]/home/server/kaldi-trunk/src/lib/libkaldi-feat.so(kaldi::OnlineGenericBaseFeature<kaldi::MfccComputer>::OnlineGenericBaseFeature(kaldi::MfccOptions const&)+0x28) [0x7f8a92e548c6]/home/server/kaldi-trunk/src/lib/libkaldi-online2.so(kaldi::OnlineNnet2FeaturePipeline::OnlineNnet2FeaturePipeline(kaldi::OnlineNnet2FeaturePipelineInfo const&)+0xcc) [0x7f8a95e0803e]./online2-wav-nnet3-latgen-faster(main+0x102f) [0x55e12e6fe4b8]/lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xe7) [0x7f8a9186abf7]./online2-wav-nnet3-latgen-faster(_start+0x2a) [0x55e12e6fc99a]./scptest.sh: 行 4: 14365 已放弃 (核心已转储)./online2-wav-nnet3-latgen-faster