[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

tools/tts/batch/clean_wenet_speech.py

@@ -1,20 +1,20 @@
 import json
-from pathlib import Path
+import os
 import subprocess
+import tempfile
+import time
+from pathlib import Path
 
 import librosa
 import soundfile as sf
 import torch
 import torchaudio
 from fish_audio_preprocess.utils.separate_audio import (
-    separate_audio,
-    merge_tracks,
     init_model,
+    merge_tracks,
+    separate_audio,
 )
 from tqdm import tqdm
-import time
-import os
-import tempfile
 
 rank = int(os.environ.get("SLURM_PROCID", 0))
 world_size = int(os.environ.get("SLURM_NTASKS", 1))
@@ -75,7 +75,9 @@ def main():
             )
             # Make it 2 channels
             audio = torch.cat([audio, audio], dim=0)
-            tracks = separate_audio(demucs, audio, shifts=1, num_workers=0, progress=False)
+            tracks = separate_audio(
+                demucs, audio, shifts=1, num_workers=0, progress=False
+            )
             audio = merge_tracks(tracks, filter=["vocals"])[0]
             vocals, sr = (
                 torchaudio.functional.resample(

tools/tts/batch/convert_to_wav.py

@@ -1,8 +1,10 @@
-from pathlib import Path
+import random
 import subprocess
 from multiprocessing import Pool, cpu_count
+from pathlib import Path
+
 from tqdm import tqdm
-import random
+
 
 def convert_to_wav(src_file_path):
     dst_file_path = dst_dir / src_file_path.relative_to(src_dir).with_suffix(".wav")
@@ -13,7 +15,19 @@ def convert_to_wav(src_file_path):
 
     try:
         subprocess.check_call(
-            ["ffmpeg", "-y", "-i", str(src_file_path), "-c:a", "pcm_s16le", "-threads", "0", "-ar", "24000", str(dst_file_path)],
+            [
+                "ffmpeg",
+                "-y",
+                "-i",
+                str(src_file_path),
+                "-c:a",
+                "pcm_s16le",
+                "-threads",
+                "0",
+                "-ar",
+                "24000",
+                str(dst_file_path),
+            ],
             stdout=subprocess.DEVNULL,
             stderr=subprocess.DEVNULL,
         )
@@ -24,6 +38,7 @@ def convert_to_wav(src_file_path):
     except subprocess.CalledProcessError:
         return False
 
+
 src_dir = Path("dataset/tts/WenetSpeech/audio/")
 dst_dir = Path("dataset/tts/WenetSpeech/audio_wav/")
 
@@ -35,13 +50,15 @@ def convert_to_wav(src_file_path):
 fail_counter = 0
 
 with Pool(processes=cpu_count() * 2, maxtasksperchild=100) as pool:
-    with tqdm(pool.imap_unordered(convert_to_wav, opus_files), total=len(opus_files)) as pbar:
+    with tqdm(
+        pool.imap_unordered(convert_to_wav, opus_files), total=len(opus_files)
+    ) as pbar:
         for success in pbar:
             if success:
                 success_counter += 1
             else:
                 fail_counter += 1
-        
+
         pbar.set_description(f"Success: {success_counter}, Fail: {fail_counter}")
 
 print(f"Successfully converted: {success_counter}")

tools/tts/batch/to_flac.py

@@ -1,16 +1,28 @@
-from pathlib import Path
+import random
 import subprocess
 from multiprocessing import Pool, cpu_count
+from pathlib import Path
+
 from tqdm import tqdm
-import random
+
 
 def convert_to_flac(src_file_path):
     dst_file_path = src_file_path.with_suffix(".flac")
     dst_file_path.parent.mkdir(parents=True, exist_ok=True)
 
     try:
         subprocess.check_call(
-            ["ffmpeg", "-y", "-i", str(src_file_path), "-acodec", "flac", "-threads", "0", str(dst_file_path)],
+            [
+                "ffmpeg",
+                "-y",
+                "-i",
+                str(src_file_path),
+                "-acodec",
+                "flac",
+                "-threads",
+                "0",
+                str(dst_file_path),
+            ],
             stdout=subprocess.DEVNULL,
             stderr=subprocess.DEVNULL,
         )
@@ -33,13 +45,15 @@ def convert_to_flac(src_file_path):
     fail_counter = 0
 
     with Pool(processes=cpu_count(), maxtasksperchild=100) as pool:
-        with tqdm(pool.imap_unordered(convert_to_flac, wav_files), total=len(wav_files)) as pbar:
+        with tqdm(
+            pool.imap_unordered(convert_to_flac, wav_files), total=len(wav_files)
+        ) as pbar:
             for success in pbar:
                 if success:
                     success_counter += 1
                 else:
                     fail_counter += 1
-            
+
             pbar.set_description(f"Success: {success_counter}, Fail: {fail_counter}")
 
     print(f"Successfully converted: {success_counter}")