Merge pull request #2 from coqui-ai/dev

Bug fix in MP3 and FLAC compute length on TTSDataset (coqui-ai#3092)

TTS/tts/datasets/dataset.py

@@ -13,6 +13,8 @@
 from TTS.utils.audio import AudioProcessor
 from TTS.utils.audio.numpy_transforms import compute_energy as calculate_energy
 
+import mutagen
+
 # to prevent too many open files error as suggested here
 # https://github.com/pytorch/pytorch/issues/11201#issuecomment-421146936
 torch.multiprocessing.set_sharing_strategy("file_system")
@@ -42,6 +44,15 @@ def string2filename(string):
     return filename
 
 
+def get_audio_size(audiopath):
+    extension = audiopath.rpartition(".")[-1].lower()
+    if extension not in {"mp3", "wav", "flac"}:
+        raise RuntimeError(f"The audio format {extension} is not supported, please convert the audio files to mp3, flac, or wav format!")
+
+    audio_info = mutagen.File(audiopath).info
+    return int(audio_info.length * audio_info.sample_rate)
+
+
 class TTSDataset(Dataset):
     def __init__(
         self,
@@ -176,7 +187,7 @@ def lengths(self):
         lens = []
         for item in self.samples:
             _, wav_file, *_ = _parse_sample(item)
-            audio_len = os.path.getsize(wav_file) / 16 * 8  # assuming 16bit audio
+            audio_len = get_audio_size(wav_file)
             lens.append(audio_len)
         return lens
 
@@ -295,7 +306,7 @@ def load_data(self, idx):
     def _compute_lengths(samples):
         new_samples = []
         for item in samples:
-            audio_length = os.path.getsize(item["audio_file"]) / 16 * 8  # assuming 16bit audio
+            audio_length = get_audio_size(item["audio_file"])
             text_lenght = len(item["text"])
             item["audio_length"] = audio_length
             item["text_length"] = text_lenght

TTS/tts/models/xtts.py

@@ -757,11 +757,13 @@ def load_checkpoint(
             checkpoint_dir = "."
         model_path = checkpoint_path or os.path.join(checkpoint_dir, "model.pth")
         vocab_path = vocab_path or os.path.join(checkpoint_dir, "vocab.json")
-        speaker_file_path = speaker_file_path or os.path.join(checkpoint_dir, "speakers_xtts.pth")
+
+        if speaker_file_path is None and checkpoint_dir is not None:
+            speaker_file_path = os.path.join(checkpoint_dir, "speakers_xtts.pth")
 
         self.language_manager = LanguageManager(config)
         self.speaker_manager = None
-        if os.path.exists(speaker_file_path):
+        if speaker_file_path is not None and os.path.exists(speaker_file_path):
             self.speaker_manager = SpeakerManager(speaker_file_path)
 
         if os.path.exists(vocab_path):

requirements.txt

@@ -17,6 +17,7 @@ pyyaml>=6.0
 fsspec>=2023.6.0 # <= 2023.9.1 makes aux tests fail
 aiohttp>=3.8.1
 packaging>=23.1
+mutagen==1.47.0
 # deps for examples
 flask>=2.0.1
 # deps for inference

tests/data/ljspeech/metadata_flac.csv

@@ -0,0 +1,9 @@
+audio_file|text|transcription|speaker_name
+wavs/LJ001-0001.flac|Printing, in the only sense with which we are at present concerned, differs from most if not from all the arts and crafts represented in the Exhibition|Printing, in the only sense with which we are at present concerned, differs from most if not from all the arts and crafts represented in the Exhibition|ljspeech-0
+wavs/LJ001-0002.flac|in being comparatively modern.|in being comparatively modern.|ljspeech-0
+wavs/LJ001-0003.flac|For although the Chinese took impressions from wood blocks engraved in relief for centuries before the woodcutters of the Netherlands, by a similar process|For although the Chinese took impressions from wood blocks engraved in relief for centuries before the woodcutters of the Netherlands, by a similar process|ljspeech-1
+wavs/LJ001-0004.flac|produced the block books, which were the immediate predecessors of the true printed book,|produced the block books, which were the immediate predecessors of the true printed book,|ljspeech-1
+wavs/LJ001-0005.flac|the invention of movable metal letters in the middle of the fifteenth century may justly be considered as the invention of the art of printing.|the invention of movable metal letters in the middle of the fifteenth century may justly be considered as the invention of the art of printing.|ljspeech-2
+wavs/LJ001-0006.flac|And it is worth mention in passing that, as an example of fine typography,|And it is worth mention in passing that, as an example of fine typography,|ljspeech-2
+wavs/LJ001-0007.flac|the earliest book printed with movable types, the Gutenberg, or "forty-two line Bible" of about 1455,|the earliest book printed with movable types, the Gutenberg, or "forty-two line Bible" of about fourteen fifty-five,|ljspeech-3
+wavs/LJ001-0008.flac|has never been surpassed.|has never been surpassed.|ljspeech-3

tests/data/ljspeech/metadata_mp3.csv

@@ -0,0 +1,9 @@
+audio_file|text|transcription|speaker_name
+wavs/LJ001-0001.mp3|Printing, in the only sense with which we are at present concerned, differs from most if not from all the arts and crafts represented in the Exhibition|Printing, in the only sense with which we are at present concerned, differs from most if not from all the arts and crafts represented in the Exhibition|ljspeech-0
+wavs/LJ001-0002.mp3|in being comparatively modern.|in being comparatively modern.|ljspeech-0
+wavs/LJ001-0003.mp3|For although the Chinese took impressions from wood blocks engraved in relief for centuries before the woodcutters of the Netherlands, by a similar process|For although the Chinese took impressions from wood blocks engraved in relief for centuries before the woodcutters of the Netherlands, by a similar process|ljspeech-1
+wavs/LJ001-0004.mp3|produced the block books, which were the immediate predecessors of the true printed book,|produced the block books, which were the immediate predecessors of the true printed book,|ljspeech-1
+wavs/LJ001-0005.mp3|the invention of movable metal letters in the middle of the fifteenth century may justly be considered as the invention of the art of printing.|the invention of movable metal letters in the middle of the fifteenth century may justly be considered as the invention of the art of printing.|ljspeech-2
+wavs/LJ001-0006.mp3|And it is worth mention in passing that, as an example of fine typography,|And it is worth mention in passing that, as an example of fine typography,|ljspeech-2
+wavs/LJ001-0007.mp3|the earliest book printed with movable types, the Gutenberg, or "forty-two line Bible" of about 1455,|the earliest book printed with movable types, the Gutenberg, or "forty-two line Bible" of about fourteen fifty-five,|ljspeech-3
+wavs/LJ001-0008.mp3|has never been surpassed.|has never been surpassed.|ljspeech-3

tests/data/ljspeech/metadata_wav.csv

@@ -0,0 +1,9 @@
+audio_file|text|transcription|speaker_name
+wavs/LJ001-0001.wav|Printing, in the only sense with which we are at present concerned, differs from most if not from all the arts and crafts represented in the Exhibition|Printing, in the only sense with which we are at present concerned, differs from most if not from all the arts and crafts represented in the Exhibition|ljspeech-0
+wavs/LJ001-0002.wav|in being comparatively modern.|in being comparatively modern.|ljspeech-0
+wavs/LJ001-0003.wav|For although the Chinese took impressions from wood blocks engraved in relief for centuries before the woodcutters of the Netherlands, by a similar process|For although the Chinese took impressions from wood blocks engraved in relief for centuries before the woodcutters of the Netherlands, by a similar process|ljspeech-1
+wavs/LJ001-0004.wav|produced the block books, which were the immediate predecessors of the true printed book,|produced the block books, which were the immediate predecessors of the true printed book,|ljspeech-1
+wavs/LJ001-0005.wav|the invention of movable metal letters in the middle of the fifteenth century may justly be considered as the invention of the art of printing.|the invention of movable metal letters in the middle of the fifteenth century may justly be considered as the invention of the art of printing.|ljspeech-2
+wavs/LJ001-0006.wav|And it is worth mention in passing that, as an example of fine typography,|And it is worth mention in passing that, as an example of fine typography,|ljspeech-2
+wavs/LJ001-0007.wav|the earliest book printed with movable types, the Gutenberg, or "forty-two line Bible" of about 1455,|the earliest book printed with movable types, the Gutenberg, or "forty-two line Bible" of about fourteen fifty-five,|ljspeech-3
+wavs/LJ001-0008.wav|has never been surpassed.|has never been surpassed.|ljspeech-3