From e5066ac1fceb499215a76ead34af0badd88a88f1 Mon Sep 17 00:00:00 2001 From: Alexandre Lissy Date: Mon, 2 Jul 2018 18:45:47 +0200 Subject: [PATCH] Fix leftover example CLI call Fixes #1429 X-DeepSpeech: NOBUILD --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 79f9aa9d..3b54612a 100644 --- a/README.md +++ b/README.md @@ -15,14 +15,14 @@ Once everything is installed you can then use the `deepspeech` binary to do spee ```bash pip3 install deepspeech -deepspeech models/output_graph.pb models/alphabet.txt my_audio_file.wav +deepspeech models/output_graph.pbmm models/alphabet.txt models/lm.binary models/trie my_audio_file.wav ``` Alternatively, quicker inference (The realtime factor on a GeForce GTX 1070 is about 0.44.) can be performed using a supported NVIDIA GPU on Linux. (See the release notes to find which GPU's are supported.) This is done by instead installing the GPU specific package: ```bash pip3 install deepspeech-gpu -deepspeech models/output_graph.pb models/alphabet.txt my_audio_file.wav +deepspeech models/output_graph.pbmm models/alphabet.txt models/lm.binary models/trie my_audio_file.wav ``` See the output of `deepspeech -h` for more information on the use of `deepspeech`. (If you experience problems running `deepspeech`, please check [required runtime dependencies](native_client/README.md#required-dependencies)).