Adding piper phonemizer with different dataset

configs/data/hi-fi_en-US_female.yaml

@@ -0,0 +1,13 @@
+defaults:
+  - ljspeech
+  - _self_
+
+_target_: matcha.data.text_mel_datamodule.TextMelDataModule
+name: hi-fi_en-US_female
+train_filelist_path: data/filelists/hi-fi-captain-en-us-female_train.txt
+valid_filelist_path: data/filelists/hi-fi-captain-en-us-female_val.txt
+batch_size: 32
+cleaners: [english_cleaners_piper]
+data_statistics:  # Computed for vctk dataset
+  mel_mean: -6.38385
+  mel_std: 2.541796

configs/experiment/hifi_dataset_piper_phonemizer.yaml

@@ -0,0 +1,14 @@
+# @package _global_
+
+# to execute this experiment run:
+# python train.py experiment=multispeaker
+
+defaults:
+  - override /data: hi-fi_en-US_female.yaml
+
+# all parameters below will be merged with parameters from default configurations set above
+# this allows you to overwrite only specified parameters
+
+tags: ["hi-fi", "single_speaker", "piper_phonemizer", "en_US", "female"]
+
+run_name: hi-fi_en-US_female_piper_phonemizer

matcha/text/cleaners.py

@@ -15,6 +15,7 @@ import logging
 import re
 
 import phonemizer
+import piper_phonemize
 from unidecode import unidecode
 
 # To avoid excessive logging we set the log level of the phonemizer package to Critical
@@ -103,3 +104,13 @@ def english_cleaners2(text):
     phonemes = global_phonemizer.phonemize([text], strip=True, njobs=1)[0]
     phonemes = collapse_whitespace(phonemes)
     return phonemes
+
+
+def english_cleaners_piper(text):
+    """Pipeline for English text, including abbreviation expansion. + punctuation + stress"""
+    text = convert_to_ascii(text)
+    text = lowercase(text)
+    text = expand_abbreviations(text)
+    phonemes = "".join(piper_phonemize.phonemize_espeak(text=text, voice="en-US")[0])
+    phonemes = collapse_whitespace(phonemes)
+    return phonemes

requirements.txt

@@ -42,3 +42,4 @@ gradio
 gdown
 wget
 seaborn
+piper_phonemize