From e16b72ff28abfb60af25c0ed6fa9dc68459f49f6 Mon Sep 17 00:00:00 2001
From: Daniel <daniel@mail.de>
Date: Fri, 3 Apr 2020 17:58:52 +0200
Subject: [PATCH] Use os.join and kenlm parameter usage description.

---
 data/lm/README.rst     | 4 +++-
 data/lm/generate_lm.py | 8 ++++----
 2 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/data/lm/README.rst b/data/lm/README.rst
index 228d210c..595cd0c0 100644
--- a/data/lm/README.rst
+++ b/data/lm/README.rst
@@ -9,7 +9,9 @@ You can download the librispeech corpus with the following commands:
     gunzip librispeech.txt.gz
 
 
-Then use the `generate_lm.py` script to generate `lm.binary` and `vocab-500000.txt`.
+| Then use the `generate_lm.py` script to generate `lm.binary` and `vocab-500000.txt`.
+| If you are not using the DeepSpeech docker container, you have to build `KenLM <https://github.com/kpu/kenlm>`_ first
+  and then pass the build path to the script `--kenlm_bins /DeepSpeech/native_client/kenlm/build/bin/`.
 
 .. code-block:: bash
 
diff --git a/data/lm/generate_lm.py b/data/lm/generate_lm.py
index 2099c2ae..4d4944f2 100644
--- a/data/lm/generate_lm.py
+++ b/data/lm/generate_lm.py
@@ -79,7 +79,7 @@ def build_lm(args, data_lower, vocab_str):
     lm_path = os.path.join(args.output_dir, "lm.arpa")
     subprocess.check_call(
         [
-            args.kenlm_bins + "lmplz",
+            os.path.join(args.kenlm_bins, "lmplz"),
             "--order",
             str(args.arpa_order),
             "--temp_prefix",
@@ -95,12 +95,12 @@ def build_lm(args, data_lower, vocab_str):
         ]
     )
 
-    # Filter LM using vocabulary of top 500k words
+    # Filter LM using vocabulary of top-k words
     print("\nFiltering ARPA file using vocabulary of top-k words ...")
     filtered_path = os.path.join(args.output_dir, "lm_filtered.arpa")
     subprocess.run(
         [
-            args.kenlm_bins + "filter",
+            os.path.join(args.kenlm_bins, "filter"),
             "single",
             "model:{}".format(lm_path),
             filtered_path,
@@ -114,7 +114,7 @@ def build_lm(args, data_lower, vocab_str):
     binary_path = os.path.join(args.output_dir, "lm.binary")
     subprocess.check_call(
         [
-            args.kenlm_bins + "build_binary",
+            os.path.join(args.kenlm_bins, "build_binary"),
             "-a",
             str(args.binary_a_bits),
             "-q",