From 36e9ea2f97395bf6e4395557fe5c80260edf62d1 Mon Sep 17 00:00:00 2001
From: Edresson Casanova <edresson1@gmail.com>
Date: Fri, 11 Mar 2022 06:43:31 -0300
Subject: [PATCH] Open bible dataset formatter (#1365)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

* Add support for voice conversion inference

* Cache d_vectors_by_speaker for fast inference using a bigger speakers.json

* Rebase bug fix

* Use the average d-vector for inference

* Fix the bug in find unique chars script

* Add OpenBible formatter

Co-authored-by: Eren Gölge <erogol@hotmail.com>
---
 TTS/bin/find_unique_chars.py   |  2 +-
 TTS/tts/datasets/formatters.py | 24 +++++++++++++++++++++++-
 2 files changed, 24 insertions(+), 2 deletions(-)

diff --git a/TTS/bin/find_unique_chars.py b/TTS/bin/find_unique_chars.py
index 4689dcad..ea169748 100644
--- a/TTS/bin/find_unique_chars.py
+++ b/TTS/bin/find_unique_chars.py
@@ -29,7 +29,7 @@ def main():
 
     items = train_items + eval_items
 
-    texts = "".join(item[0] for item in items)
+    texts = "".join(item["text"] for item in items)
     chars = set(texts)
     lower_chars = filter(lambda c: c.islower(), chars)
     chars_force_lower = [c.lower() for c in chars]
diff --git a/TTS/tts/datasets/formatters.py b/TTS/tts/datasets/formatters.py
index ac3080c3..573a5deb 100644
--- a/TTS/tts/datasets/formatters.py
+++ b/TTS/tts/datasets/formatters.py
@@ -348,7 +348,29 @@ def vctk_old(root_path, meta_files=None, wavs_path="wav48", ignored_speakers=Non
         with open(meta_file, "r", encoding="utf-8") as file_text:
             text = file_text.readlines()[0]
         wav_file = os.path.join(root_path, wavs_path, speaker_id, file_id + ".wav")
-        items.append({"text": text, "audio_file": wav_file, "speaker_name": "VCTK_" + speaker_id})
+        items.append({"text": text, "audio_file": wav_file, "speaker_name": "VCTK_old_" + speaker_id})
+    return items
+
+
+def open_bible(root_path, meta_files="train", ignore_digits_sentences=True, ignored_speakers=None):
+    """ToDo: Refer the paper when available"""
+    items = []
+    split_dir = meta_files
+    meta_files = glob(f"{os.path.join(root_path, split_dir)}/**/*.txt", recursive=True)
+    for meta_file in meta_files:
+        _, speaker_id, txt_file = os.path.relpath(meta_file, root_path).split(os.sep)
+        file_id = txt_file.split(".")[0]
+        # ignore speakers
+        if isinstance(ignored_speakers, list):
+            if speaker_id in ignored_speakers:
+                continue
+        with open(meta_file, "r", encoding="utf-8") as file_text:
+            text = file_text.readline().replace("\n", "")
+        # ignore sentences that contains digits
+        if ignore_digits_sentences and any(map(str.isdigit, text)):
+            continue
+        wav_file = os.path.join(root_path, split_dir, speaker_id, file_id + ".flac")
+        items.append({"text": text, "audio_file": wav_file, "speaker_name": "OB_" + speaker_id})
     return items