From 8b43ec9a640563719940dccd8211724373416049 Mon Sep 17 00:00:00 2001
From: babysor00 <babysor00@gmail.com>
Date: Tue, 12 Oct 2021 20:01:37 +0800
Subject: [PATCH] Fix bug pre-processing magicdata

---
 synthesizer/preprocess.py            |  5 +++--
 synthesizer/preprocess_transcript.py | 11 ++++++++++-
 2 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/synthesizer/preprocess.py b/synthesizer/preprocess.py
index 430b037..c4779ed 100644
--- a/synthesizer/preprocess.py
+++ b/synthesizer/preprocess.py
@@ -7,7 +7,7 @@ from tqdm import tqdm
 import numpy as np
 from encoder import inference as encoder
 from synthesizer.preprocess_speaker import preprocess_speaker_general
-from synthesizer.preprocess_transcript import preprocess_transcript_aishell3
+from synthesizer.preprocess_transcript import preprocess_transcript_aishell3, preprocess_transcript_magicdata
 
 data_info = {
     "aidatatang_200zh": {
@@ -18,7 +18,8 @@ data_info = {
     "magicdata": {
         "subfolders": ["train"],
         "trans_filepath": "train/TRANS.txt",
-        "speak_func": preprocess_speaker_general
+        "speak_func": preprocess_speaker_general,
+        "transcript_func": preprocess_transcript_magicdata,
     },
     "aishell3":{
         "subfolders": ["train/wav"],
diff --git a/synthesizer/preprocess_transcript.py b/synthesizer/preprocess_transcript.py
index 8810a92..7a26672 100644
--- a/synthesizer/preprocess_transcript.py
+++ b/synthesizer/preprocess_transcript.py
@@ -6,4 +6,13 @@ def preprocess_transcript_aishell3(dict_info, dict_transcript):
         transList = []
         for i in range(2, len(v), 2):
             transList.append(v[i])
-        dict_info[v[0]] = " ".join(transList)
\ No newline at end of file
+        dict_info[v[0]] = " ".join(transList)
+
+
+def preprocess_transcript_magicdata(dict_info, dict_transcript):
+    for v in dict_transcript:
+        if not v:
+            continue
+        v = v.strip().replace("\n","").replace("\t"," ").split(" ")
+        dict_info[v[0]] = " ".join(v[2:])
+       
\ No newline at end of file