From f449105b79a9367ed51325b718308df92963bd8b Mon Sep 17 00:00:00 2001
From: Malar Kannan <malarkannan.invention@gmail.com>
Date: Mon, 23 Sep 2019 16:26:54 +0530
Subject: [PATCH] 1. updated requirements 2. spm params explicit 3. gitignore
 and script

---
 .gitignore       | 2 ++
 requirements.txt | 4 ++--
 spm_codec.py     | 6 +++---
 3 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/.gitignore b/.gitignore
index 4afec03..acc83b2 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,6 +1,8 @@
 .env
 env/
 jupyter.json
+run*/
+filelists/
 # Created by https://www.gitignore.io/api/macos
 # Edit at https://www.gitignore.io/?templates=macos
 
diff --git a/requirements.txt b/requirements.txt
index 11eccea..49e76b5 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,6 +1,6 @@
 matplotlib==2.1.0
-tensorflow
-numpy==1.13.3
+tensorflow==1.1.0
+numpy==1.17.1
 inflect==0.2.5
 librosa==0.6.0
 scipy==1.0.0
diff --git a/spm_codec.py b/spm_codec.py
index c677643..92cdb9f 100644
--- a/spm_codec.py
+++ b/spm_codec.py
@@ -25,7 +25,7 @@ def _create_sentencepiece_corpus():
 
 
 def _create_sentencepiece_vocab(vocab_size=SPM_VOCAB_SIZE):
-    train_params = "--input={} --model_prefix={} --vocab_size={}".format(
+    train_params = "--input={} --model_type=unigram --character_coverage=1.0 --model_prefix={} --vocab_size={}".format(
         SPM_CORPUS_FILE, SPM_MODEL_PREFIX, vocab_size
     )
     spm.SentencePieceTrainer.Train(train_params)
@@ -56,8 +56,8 @@ def _interactive_test():
 
 
 def main():
-    # _create_sentencepiece_corpus()
-    # _create_sentencepiece_vocab()
+    _create_sentencepiece_corpus()
+    _create_sentencepiece_vocab()
     _interactive_test()