Created by: aslily1234

通过docker配置的环境，执行到sh run_infer.sh 报错，模型下载路径已经修改了 English LM LibriSpeech Model

root@6c5480fbb525:/DeepSpeech/examples/tiny# sh run_infer.sh Download language model ... download_lm_en.sh: 8: [: 099a601759d467cd0a8523ff939819c5: unexpected operator --2019-05-08 10:25:03-- https://deepspeech.bj.bcebos.com/en_lm/common_crawl_00.prune01111.trie.klm Resolving deepspeech.bj.bcebos.com (deepspeech.bj.bcebos.com)... 180.149.142.214, 220.181.33.43 Connecting to deepspeech.bj.bcebos.com (deepspeech.bj.bcebos.com)|180.149.142.214|:443... connected. HTTP request sent, awaiting response... 416 Requested Range Not Satisfiable

The file is already fully retrieved; nothing to do.

download_lm_en.sh: 20: [: 099a601759d467cd0a8523ff939819c5: unexpected operator ----------- Configuration Arguments ----------- alpha: 2.5 beam_size: 500 beta: 0.3 cutoff_prob: 1.0 cutoff_top_n: 40 decoding_method: ctc_beam_search error_rate_type: wer infer_manifest: data/tiny/manifest.tiny lang_model_path: models/lm/common_crawl_00.prune01111.trie.klm mean_std_path: data/tiny/mean_std.npz model_path: checkpoints/tiny/params.pass-19.tar.gz num_conv_layers: 2 num_proc_bsearch: 8 num_rnn_layers: 3 num_samples: 10 rnn_layer_size: 2048 share_rnn_weights: 1 specgram_type: linear trainer_count: 1 use_gpu: 1 use_gru: 0 vocab_path: data/tiny/vocab.txt

I0508 10:25:22.147784 89 Util.cpp:166] commandline: --use_gpu=1 --rnn_use_batch=True --trainer_count=1 [INFO 2019-05-08 10:25:26,183 layers.py:2606] output for conv_0: c = 32, h = 81, w = 54, size = 139968 [INFO 2019-05-08 10:25:26,184 layers.py:3133] output for batch_norm_0: c = 32, h = 81, w = 54, size = 139968 [INFO 2019-05-08 10:25:26,185 layers.py:7224] output for scale_sub_region_0: c = 32, h = 81, w = 54, size = 139968 [INFO 2019-05-08 10:25:26,186 layers.py:2606] output for conv_1: c = 32, h = 41, w = 54, size = 70848 [INFO 2019-05-08 10:25:26,187 layers.py:3133] output for batch_norm_1: c = 32, h = 41, w = 54, size = 70848 [INFO 2019-05-08 10:25:26,187 layers.py:7224] output for scale_sub_region_1: c = 32, h = 41, w = 54, size = 70848 [INFO 2019-05-08 10:25:30,907 model.py:243] begin to initialize the external scorer for decoding Loading the LM will be faster if you build a binary file. Reading models/lm/common_crawl_00.prune01111.trie.klm ----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100 terminate called after throwing an instance of 'util::CompressedException' what(): kenlm/util/read_compressed.cc:376 in util::ReadBase* util::{anonymous}::ReadFactory(int, uint64_t&, const void*, std::size_t, bool) threw CompressedException. This looks like a gzip file but gzip support was not compiled in. in file models/lm/common_crawl_00.prune01111.trie.klm *** Aborted at 1557311130 (unix time) try "date -d @1557311130" if you are using GNU date *** PC: @ 0x0 (unknown) *** SIGABRT (@0x59) received by PID 89 (TID 0x7fc83aaa1700) from PID 89; stack trace: *** @ 0x7fc83a67d390 (unknown) @ 0x7fc83a2d7428 gsignal @ 0x7fc83a2d902a abort @ 0x7fc8227d084d __gnu_cxx::__verbose_terminate_handler() @ 0x7fc8227ce6b6 (unknown) @ 0x7fc8227ce701 std::terminate() @ 0x7fc8227ce969 __cxa_rethrow @ 0x7fc817195c24 util::FilePiece::TransitionToRead() @ 0x7fc8171966f9 util::FilePiece::FilePiece() @ 0x7fc8171a9ee1 lm::ngram::detail::GenericModel<>::InitializeFromARPA() @ 0x7fc8171ac13b lm::ngram::detail::GenericModel<>::GenericModel() @ 0x7fc8171a33db lm::ngram::LoadVirtual() @ 0x7fc8172d4a5f Scorer::load_lm() @ 0x7fc8172d8041 Scorer::setup() @ 0x7fc8172d813d Scorer::Scorer() @ 0x7fc817292f48 _wrap_new_Scorer @ 0x4c468a PyEval_EvalFrameEx @ 0x4c2765 PyEval_EvalCodeEx @ 0x4de6fe (unknown) @ 0x4b0cb3 PyObject_Call @ 0x4f492e (unknown) @ 0x4b0cb3 PyObject_Call @ 0x4c9faf PyEval_EvalFrameEx @ 0x4c2765 PyEval_EvalCodeEx @ 0x4de6fe (unknown) @ 0x4b0cb3 PyObject_Call @ 0x4f492e (unknown) @ 0x4b0cb3 PyObject_Call @ 0x4f46a7 (unknown) @ 0x4b670c (unknown) @ 0x4b0cb3 PyObject_Call @ 0x4c9faf PyEval_EvalFrameEx Aborted (core dumped) Failed in inference!