Merge pull request #205 from sonphantrung/various-fixes

Various fixes.

.github/workflows/unittest.yml

@@ -0,0 +1,36 @@
+name: Unit Test
+on: [ push, pull_request ]
+jobs:
+  build:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        python-version: ["3.9", "3.10"]
+        os: [ubuntu-latest]
+      fail-fast: true
+
+    steps:
+    - uses: actions/checkout@master
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v4
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: |
+        sudo apt update
+        sudo apt -y install ffmpeg
+        sudo apt -y install -qq aria2
+        aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/hubert_base.pt -d ./ -o hubert_base.pt
+        python -m pip install --upgrade pip
+        python -m pip install --upgrade setuptools
+        python -m pip install --upgrade wheel
+        pip install torch torchvision torchaudio
+        pip install -r requirements.txt
+    - name: Test step 1 & 2
+      run: |
+        mkdir -p logs/mi-test
+        touch logs/mi-test/preprocess.log
+        python rvc/train/preprocess/preprocess.py logs/mi-test logs/mute/0_gt_wavs 48000 8 3.7
+        touch logs/mi-test/extract_f0_feature.log
+        python rvc/train/extract/extract_f0_print.py logs/mi-test pm 64
+        python rvc/train/extract/extract_feature_print.py cpu 1 0 0 logs/mi-test v1 True

rvc/train/extract/extract_feature_print.py

@@ -13,11 +13,11 @@
 i_part = int(sys.argv[3])
 
 if len(sys.argv) == 7:
-    exp_dir, version, is_half = sys.argv[4], sys.argv[5], sys.argv[6]
+    exp_dir, version, is_half = sys.argv[4], sys.argv[5], bool(sys.argv[6])
 else:
     i_gpu, exp_dir = sys.argv[4], sys.argv[5]
     os.environ["CUDA_VISIBLE_DEVICES"] = str(i_gpu)
-    version, is_half = sys.argv[6], sys.argv[7]
+    version, is_half = sys.argv[6], bool(sys.argv[7])
 
 
 def forward_dml(ctx, x, scale):

rvc/train/slicer.py

@@ -1,10 +1,8 @@
 import os
-from argparse import ArgumentParser
 import librosa
 import soundfile
 import numpy as np
 
-
 class Slicer:
     def __init__(
         self,
@@ -144,7 +142,6 @@ def slice(self, waveform):
 
             return chunks
 
-
 def get_rms(
     y,
     frame_length=2048,
@@ -173,72 +170,3 @@ def get_rms(
 
     power = np.mean(np.abs(x) ** 2, axis=-2, keepdims=True)
     return np.sqrt(power)
-
-
-def main():
-    parser = ArgumentParser()
-    parser.add_argument("audio", type=str, help="The audio to be sliced")
-    parser.add_argument(
-        "--out", type=str, help="Output directory of the sliced audio clips"
-    )
-    parser.add_argument(
-        "--db_thresh",
-        type=float,
-        default=-40,
-        help="The dB threshold for silence detection",
-    )
-    parser.add_argument(
-        "--min_length",
-        type=int,
-        default=5000,
-        help="The minimum milliseconds required for each sliced audio clip",
-    )
-    parser.add_argument(
-        "--min_interval",
-        type=int,
-        default=300,
-        help="The minimum milliseconds for a silence part to be sliced",
-    )
-    parser.add_argument(
-        "--hop_size", type=int, default=10, help="Frame length in milliseconds"
-    )
-    parser.add_argument(
-        "--max_sil_kept",
-        type=int,
-        default=500,
-        help="The maximum silence length kept around the sliced clip, presented in milliseconds",
-    )
-    args = parser.parse_args()
-
-    out = args.out or os.path.dirname(os.path.abspath(args.audio))
-    audio, sr = librosa.load(args.audio, sr=None, mono=False)
-
-    slicer = Slicer(
-        sr=sr,
-        threshold=args.db_thresh,
-        min_length=args.min_length,
-        min_interval=args.min_interval,
-        hop_size=args.hop_size,
-        max_sil_kept=args.max_sil_kept,
-    )
-
-    chunks = slicer.slice(audio)
-
-    if not os.path.exists(out):
-        os.makedirs(out)
-
-    for i, chunk in enumerate(chunks):
-        if len(chunk.shape) > 1:
-            chunk = chunk.T
-        soundfile.write(
-            os.path.join(
-                out,
-                f"{os.path.basename(args.audio).rsplit('.', maxsplit=1)[0]}_{i}.wav",
-            ),
-            chunk,
-            sr,
-        )
-
-
-if __name__ == "__main__":
-    main()

rvc/train/train.py

@@ -43,7 +43,7 @@
     kl_loss,
 )
 from mel_processing import mel_spectrogram_torch, spec_to_mel_torch
-from process_ckpt import save_final
+from process_ckpt import save_final, extract_small_model
 
 from rvc.lib.infer_pack import commons
 
@@ -560,7 +560,7 @@ def train_and_evaluate(rank, epoch, hps, nets, optims, scaler, loaders, writers,
                 % (
                     hps.name,
                     epoch,
-                    save_final(
+                    extract_small_model(
                         ckpt,
                         hps.sample_rate,
                         hps.if_f0,

tabs/inference/inference.py

@@ -1,6 +1,6 @@
 import os, sys
 import gradio as gr
-import regex as re
+import re
 import shutil
 import datetime
 import random

tabs/train/train.py

@@ -69,6 +69,7 @@ def train_tab():
                 model_name = gr.Textbox(
                     label=i18n("Model Name"),
                     placeholder=i18n("Enter model name"),
+                    value="my-project",
                     interactive=True,
                 )
                 dataset_path = gr.Textbox(