Init commit

.gitignore

@@ -0,0 +1,6 @@
+env/
+*.mp3
+*.pt
+*.index
+*.pth
+*.npy

README.md

@@ -0,0 +1,5 @@
+---
+license: mit
+title: Rvc
+sdk: gradio
+---

app.py

@@ -0,0 +1,160 @@
+import gradio as gr
+from infer_rvc_python import BaseLoader
+import random
+from urllib.request import urlretrieve
+
+files_to_retrieve = [
+    "https://replicate.delivery/pbxt/N97QM3XNFrooJhV6Fb0meBff0aAG1rEDfvuxcdLS6fTx1vmWC/test.zip",
+    "https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/hubert_base.pt?download=true",
+    "https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/rmvpe.pt?download=true"
+    ]
+
+for file in files_to_retrieve:
+    print(f"Downloading {file}")
+    urlretrieve(file, file.split("/")[-1])
+
+# unzip test.zip
+import zipfile
+with zipfile.ZipFile("test.zip", 'r') as zip_ref:
+    zip_ref.extractall(".")
+
+
+converter = BaseLoader(
+    only_cpu=True, hubert_path="./hubert_base.pt", rmvpe_path="./rmvpe.pt"
+)
+
+model = "test.pth"
+index = "added_IVF839_Flat_nprobe_1_test_v2.index"
+
+
+
+
+
+def voice_conversion(
+    audio,
+    pitch_change,
+    filter_radius,
+    envelope_ratio,
+    index_influence,
+    consonant_breath_protection,
+):
+    audio_out = run(
+        [str(audio)],
+        model,
+        "rmvpe+",
+        pitch_change,
+        index,
+        index_influence,
+        filter_radius,
+        envelope_ratio,
+        consonant_breath_protection,
+    )
+    print(audio_out)
+    return audio_out[0]
+
+
+
+def convert_now(audio_files, random_tag):
+    return converter(audio_files, random_tag, overwrite=False, parallel_workers=8)
+
+
+def run(
+    audio_files,
+    file_m,
+    pitch_alg,
+    pitch_lvl,
+    file_index,
+    index_inf,
+    r_m_f,
+    e_r,
+    c_b_p,
+):
+    random_tag = "USER_" + str(random.randint(10000000, 99999999))
+
+    converter.apply_conf(
+        tag=random_tag,
+        file_model=file_m,
+        pitch_algo=pitch_alg,
+        pitch_lvl=pitch_lvl,
+        file_index=file_index,
+        index_influence=index_inf,
+        respiration_median_filtering=r_m_f,
+        envelope_ratio=e_r,
+        consonant_breath_protection=c_b_p,
+        resample_sr=44100 if audio_files[0].endswith(".mp3") else 0,
+    )
+
+    return convert_now(audio_files, random_tag)
+
+
+
+# Create the Gradio interface
+# audio_input = gr.Audio(type="file")
+# audio_output = gr.Audio(type="file")
+
+# gr.Interface(fn=voice_conversion, inputs=audio_input, outputs=audio_output).launch()
+
+
+def ui():
+    with gr.Blocks() as demo:
+        audio_input = gr.Audio(sources=["microphone", "upload"], type="filepath")
+        with gr.Row():
+            pitch_slider = gr.Slider(
+                minimum=-24,
+                maximum=24,
+                value=0,
+                step=1,
+                label="Pitch",
+                interactive=True,
+            )
+            index_influence_slider = gr.Slider(
+                minimum=0,
+                maximum=1,
+                value=0.75,
+                step=0.01,
+                label="Index Influence",
+                interactive=True,
+            )
+            respiration_median_filtering = gr.Slider(
+                minimum=0,
+                maximum=10,
+                value=3,
+                step=1,
+                label="Resp. Median Filtering",
+                interactive=True,
+            )
+            envelope_ratio = gr.Slider(
+                minimum=0,
+                maximum=1,
+                value=0.25,
+                step=0.01,
+                label="Envelope Ratio",
+                interactive=True,
+            )
+            consonant_breath_protection = gr.Slider(
+                minimum=0,
+                maximum=1,
+                value=0.5,
+                step=0.01,
+                label="Consonant Breath Protection",
+                interactive=True,
+            )
+        button = gr.Button("Convert")
+        audio_output = gr.Audio(type="filepath")
+        button.click(
+            voice_conversion,
+            inputs=[
+                audio_input,
+                pitch_slider,
+                respiration_median_filtering,
+                envelope_ratio,
+                index_influence_slider,
+                consonant_breath_protection,
+            ],
+            outputs=audio_output,
+        )
+
+    return demo
+
+
+ui().launch()

gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

inference.py

@@ -0,0 +1,65 @@
+import os
+
+# import gradio as gr
+# import spaces
+from infer_rvc_python import BaseLoader
+import random
+import logging
+import time
+import soundfile as sf
+from infer_rvc_python.main import download_manager
+import zipfile
+
+converter = BaseLoader(
+    only_cpu=True, hubert_path="./hubert_base.pt", rmvpe_path="./rmvpe.pt"
+)
+
+
+def main():
+    audio_out = run(
+        ["super-shy-mdx.mp3"],
+        "test.pth",
+        "rmvpe+",
+        -12,
+        "added_IVF839_Flat_nprobe_1_test_v2.index",
+        0.75,  # index_influence
+        3,  # respiration_median_filtering,
+        0.25,  # envelope_ratio,
+        0.5,  # consonant_breath_protection
+    )
+
+
+def convert_now(audio_files, random_tag, converter):
+    return converter(audio_files, random_tag, overwrite=False, parallel_workers=0)
+
+
+def run(
+    audio_files,
+    file_m,
+    pitch_alg,
+    pitch_lvl,
+    file_index,
+    index_inf,
+    r_m_f,
+    e_r,
+    c_b_p,
+):
+    random_tag = "USER_" + str(random.randint(10000000, 99999999))
+
+    converter.apply_conf(
+        tag=random_tag,
+        file_model=file_m,
+        pitch_algo=pitch_alg,
+        pitch_lvl=pitch_lvl,
+        file_index=file_index,
+        index_influence=index_inf,
+        respiration_median_filtering=r_m_f,
+        envelope_ratio=e_r,
+        consonant_breath_protection=c_b_p,
+        resample_sr=44100 if audio_files[0].endswith(".mp3") else 0,
+    )
+
+    return convert_now(audio_files, random_tag, converter)
+
+if __name__ == "__main__":
+    main()

playground.ipynb

@@ -0,0 +1,164 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "# import gradio as gr\n",
+    "# import spaces\n",
+    "from infer_rvc_python import BaseLoader\n",
+    "import random\n",
+    "import logging\n",
+    "import time\n",
+    "import soundfile as sf\n",
+    "from infer_rvc_python.main import download_manager\n",
+    "import zipfile"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "converter = BaseLoader(only_cpu=False, hubert_path=\"./hubert_base.pt\", rmvpe_path=\"./rmvpe.pt\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def convert_now(audio_files, random_tag, converter):\n",
+    "    return converter(\n",
+    "        audio_files,\n",
+    "        random_tag,\n",
+    "        overwrite=False,\n",
+    "        parallel_workers=8\n",
+    "    )\n",
+    "\n",
+    "\n",
+    "def run(\n",
+    "    audio_files,\n",
+    "    file_m,\n",
+    "    pitch_alg,\n",
+    "    pitch_lvl,\n",
+    "    file_index,\n",
+    "    index_inf,\n",
+    "    r_m_f,\n",
+    "    e_r,\n",
+    "    c_b_p,\n",
+    "):\n",
+    "    random_tag = \"USER_\"+str(random.randint(10000000, 99999999))\n",
+    "\n",
+    "    converter.apply_conf(\n",
+    "        tag=random_tag,\n",
+    "        file_model=file_m,\n",
+    "        pitch_algo=pitch_alg,\n",
+    "        pitch_lvl=pitch_lvl,\n",
+    "        file_index=file_index,\n",
+    "        index_influence=index_inf,\n",
+    "        respiration_median_filtering=r_m_f,\n",
+    "        envelope_ratio=e_r,\n",
+    "        consonant_breath_protection=c_b_p,\n",
+    "        resample_sr=44100 if audio_files[0].endswith('.mp3') else 0, \n",
+    "    )\n",
+    "\n",
+    "    return convert_now(audio_files, random_tag, converter)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[INFO] >> Supported N-card not found, using MPS for inference\n",
+      "[INFO] >> Config: Device is mps, half precision is True\n",
+      "[INFO] >> Parallel workers: 8\n",
+      "Progress:   0%|          | 0/1 [00:00<?, ?it/s][INFO] >> Loading test.pth\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "gin_channels: 256 self.spk_embed_dim: 109\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[INFO] >> Loading vocal pitch estimator model\n"
+     ]
+    },
+    {
+     "ename": "KeyboardInterrupt",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[4], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mrun\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m      2\u001b[0m \u001b[43m    \u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43msuper-shy-mdx.mp3\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m      3\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtest.pth\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m      4\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mrmvpe+\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m      5\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;241;43m-\u001b[39;49m\u001b[38;5;241;43m12\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m      6\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43madded_IVF839_Flat_nprobe_1_test_v2.index\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m      7\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;241;43m0.75\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;66;43;03m# index_influence\u001b[39;49;00m\n\u001b[1;32m      8\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;241;43m3\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;66;43;03m# respiration_median_filtering,\u001b[39;49;00m\n\u001b[1;32m      9\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;241;43m0.25\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;66;43;03m# envelope_ratio,\u001b[39;49;00m\n\u001b[1;32m     10\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;241;43m0.5\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;66;43;03m# consonant_breath_protection\u001b[39;49;00m\n\u001b[1;32m     11\u001b[0m \u001b[43m)\u001b[49m\n",
+      "Cell \u001b[0;32mIn[3], line 36\u001b[0m, in \u001b[0;36mrun\u001b[0;34m(audio_files, file_m, pitch_alg, pitch_lvl, file_index, index_inf, r_m_f, e_r, c_b_p)\u001b[0m\n\u001b[1;32m     21\u001b[0m random_tag \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mUSER_\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;241m+\u001b[39m\u001b[38;5;28mstr\u001b[39m(random\u001b[38;5;241m.\u001b[39mrandint(\u001b[38;5;241m10000000\u001b[39m, \u001b[38;5;241m99999999\u001b[39m))\n\u001b[1;32m     23\u001b[0m converter\u001b[38;5;241m.\u001b[39mapply_conf(\n\u001b[1;32m     24\u001b[0m     tag\u001b[38;5;241m=\u001b[39mrandom_tag,\n\u001b[1;32m     25\u001b[0m     file_model\u001b[38;5;241m=\u001b[39mfile_m,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m     33\u001b[0m     resample_sr\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m44100\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m audio_files[\u001b[38;5;241m0\u001b[39m]\u001b[38;5;241m.\u001b[39mendswith(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m.mp3\u001b[39m\u001b[38;5;124m'\u001b[39m) \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;241m0\u001b[39m, \n\u001b[1;32m     34\u001b[0m )\n\u001b[0;32m---> 36\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mconvert_now\u001b[49m\u001b[43m(\u001b[49m\u001b[43maudio_files\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrandom_tag\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mconverter\u001b[49m\u001b[43m)\u001b[49m\n",
+      "Cell \u001b[0;32mIn[3], line 2\u001b[0m, in \u001b[0;36mconvert_now\u001b[0;34m(audio_files, random_tag, converter)\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mconvert_now\u001b[39m(audio_files, random_tag, converter):\n\u001b[0;32m----> 2\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mconverter\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m      3\u001b[0m \u001b[43m        \u001b[49m\u001b[43maudio_files\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m      4\u001b[0m \u001b[43m        \u001b[49m\u001b[43mrandom_tag\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m      5\u001b[0m \u001b[43m        \u001b[49m\u001b[43moverwrite\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m      6\u001b[0m \u001b[43m        \u001b[49m\u001b[43mparallel_workers\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m8\u001b[39;49m\n\u001b[1;32m      7\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/Developer/playground/rvc-infer-demo/env/lib/python3.10/site-packages/infer_rvc_python/main.py:780\u001b[0m, in \u001b[0;36mBaseLoader.__call__\u001b[0;34m(self, audio_files, tag_list, overwrite, parallel_workers, type_output)\u001b[0m\n\u001b[1;32m    778\u001b[0m \u001b[38;5;66;03m# Run last\u001b[39;00m\n\u001b[1;32m    779\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m threads:\n\u001b[0;32m--> 780\u001b[0m     \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrun_threads\u001b[49m\u001b[43m(\u001b[49m\u001b[43mthreads\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    782\u001b[0m progress_bar\u001b[38;5;241m.\u001b[39mupdate(\u001b[38;5;28mlen\u001b[39m(threads))\n\u001b[1;32m    783\u001b[0m progress_bar\u001b[38;5;241m.\u001b[39mclose()\n",
+      "File \u001b[0;32m~/Developer/playground/rvc-infer-demo/env/lib/python3.10/site-packages/infer_rvc_python/main.py:563\u001b[0m, in \u001b[0;36mBaseLoader.run_threads\u001b[0;34m(self, threads)\u001b[0m\n\u001b[1;32m    561\u001b[0m \u001b[38;5;66;03m# Wait for all threads to finish\u001b[39;00m\n\u001b[1;32m    562\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m thread \u001b[38;5;129;01min\u001b[39;00m threads:\n\u001b[0;32m--> 563\u001b[0m     \u001b[43mthread\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mjoin\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    565\u001b[0m gc\u001b[38;5;241m.\u001b[39mcollect()\n\u001b[1;32m    566\u001b[0m torch\u001b[38;5;241m.\u001b[39mcuda\u001b[38;5;241m.\u001b[39mempty_cache()\n",
+      "File \u001b[0;32m/opt/homebrew/Cellar/[email protected]/3.10.14/Frameworks/Python.framework/Versions/3.10/lib/python3.10/threading.py:1096\u001b[0m, in \u001b[0;36mThread.join\u001b[0;34m(self, timeout)\u001b[0m\n\u001b[1;32m   1093\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mRuntimeError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcannot join current thread\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m   1095\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m timeout \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m-> 1096\u001b[0m     \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_wait_for_tstate_lock\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1097\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m   1098\u001b[0m     \u001b[38;5;66;03m# the behavior of a negative timeout isn't documented, but\u001b[39;00m\n\u001b[1;32m   1099\u001b[0m     \u001b[38;5;66;03m# historically .join(timeout=x) for x<0 has acted as if timeout=0\u001b[39;00m\n\u001b[1;32m   1100\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_wait_for_tstate_lock(timeout\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mmax\u001b[39m(timeout, \u001b[38;5;241m0\u001b[39m))\n",
+      "File \u001b[0;32m/opt/homebrew/Cellar/[email protected]/3.10.14/Frameworks/Python.framework/Versions/3.10/lib/python3.10/threading.py:1116\u001b[0m, in \u001b[0;36mThread._wait_for_tstate_lock\u001b[0;34m(self, block, timeout)\u001b[0m\n\u001b[1;32m   1113\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m\n\u001b[1;32m   1115\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m-> 1116\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[43mlock\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43macquire\u001b[49m\u001b[43m(\u001b[49m\u001b[43mblock\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[43m)\u001b[49m:\n\u001b[1;32m   1117\u001b[0m         lock\u001b[38;5;241m.\u001b[39mrelease()\n\u001b[1;32m   1118\u001b[0m         \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_stop()\n",
+      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
+     ]
+    }
+   ],
+   "source": [
+    "run(\n",
+    "    [\"super-shy-mdx.mp3\"],\n",
+    "    \"test.pth\",\n",
+    "    \"rmvpe+\",\n",
+    "    -12,\n",
+    "    \"added_IVF839_Flat_nprobe_1_test_v2.index\",\n",
+    "    0.75, # index_influence\n",
+    "    3, # respiration_median_filtering,\n",
+    "    0.25, # envelope_ratio,\n",
+    "    0.5, # consonant_breath_protection\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "env",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.14"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

requirements.txt

@@ -0,0 +1 @@
+infer-rvc-python