From f09ea11c71e70eded15bc637786048095a71d096 Mon Sep 17 00:00:00 2001
From: WeberJulian <julian.weber@hotmail.fr>
Date: Wed, 8 Jun 2022 14:31:03 +0200
Subject: [PATCH] Internal formatter (#1629)

* Add coqui formatter

* Make style
---
 TTS/tts/datasets/formatters.py | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/TTS/tts/datasets/formatters.py b/TTS/tts/datasets/formatters.py
index ac9e87dc..1e95c60f 100644
--- a/TTS/tts/datasets/formatters.py
+++ b/TTS/tts/datasets/formatters.py
@@ -5,6 +5,7 @@ from glob import glob
 from pathlib import Path
 from typing import List
 
+import pandas as pd
 from tqdm import tqdm
 
 ########################
@@ -12,6 +13,34 @@ from tqdm import tqdm
 ########################
 
 
+def coqui(root_path, meta_file, ignored_speakers=None):
+    """Interal dataset formatter."""
+    metadata = pd.read_csv(os.path.join(root_path, meta_file), sep="|")
+    assert all(x in metadata.columns for x in ["audio_file", "text"])
+    speaker_name = None if "speaker_name" in metadata.columns else "coqui"
+    emotion_name = None if "emotion_name" in metadata.columns else "neutral"
+    items = []
+    not_found_counter = 0
+    for row in metadata.itertuples():
+        if speaker_name is None and ignored_speakers is not None and row.speaker_name in ignored_speakers:
+            continue
+        audio_path = os.path.join(root_path, row.audio_file)
+        if not os.path.exists(audio_path):
+            not_found_counter += 1
+            continue
+        items.append(
+            {
+                "text": row.text,
+                "audio_file": audio_path,
+                "speaker_name": speaker_name if speaker_name is not None else row.speaker_name,
+                "emotion_name": emotion_name if emotion_name is not None else row.emotion_name,
+            }
+        )
+    if not_found_counter > 0:
+        print(f" | > [!] {not_found_counter} files not found")
+    return items
+
+
 def tweb(root_path, meta_file, **kwargs):  # pylint: disable=unused-argument
     """Normalize TWEB dataset.
     https://www.kaggle.com/bryanpark/the-world-english-bible-speech-dataset