无法运行Deepspeech的麦克风VAD流

Question

我下载了用于测试DeepSpeech的模型目录。当我按照here的说明进行操作时，我得到了这个错误：

python3 mic_vad_streaming.py --model deepspeech-0.6.1-models/output_graph.pbmm
Initializing model...
INFO:root:ARGS.model: deepspeech-0.6.1-models/output_graph.pbmm
TensorFlow: v1.14.0-21-ge77504a
DeepSpeech: v0.6.0-0-g6d43e21
2020-02-25 15:57:17.741956: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
INFO:root:ARGS.lm: lm.binary
INFO:root:ARGS.trie: trie
[native_client/ctcdecode/scorer.cpp:77] FATAL: "(access(filename, 4)) == (0)" check failed. Invalid language model pathSegmentation fault (core dumped)

有人能帮我找出哪里出了问题吗？

Answer 1

我也面临着同样的问题。只需使用下面的命令

$ export TF_CPP_MIN_LOG_LEVEL=2