Upload 16 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+model.index filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,12 +1,14 @@
----
-title: Vodex AI
-emoji: 🏃
-colorFrom: blue
-colorTo: red
-sdk: gradio
-sdk_version: 4.41.0
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: RVC⚡ZERO
+emoji: ⚡
+colorFrom: gray
+colorTo: indigo
+sdk: gradio
+sdk_version: 4.28.3
+app_file: app.py
+license: mit
+pinned: true
+short_description: Voice conversion framework based on VITS
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,360 @@
+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
+import edge_tts
+import asyncio
+import librosa
+import traceback
+import soundfile as sf
+from pedalboard import Pedalboard, Reverb, Compressor, HighpassFilter
+from pedalboard.io import AudioFile
+from pydub import AudioSegment
+import noisereduce as nr
+import numpy as np
+import urllib.request
+import shutil
+import threading
+
+logging.getLogger("infer_rvc_python").setLevel(logging.ERROR)
+
+converter = BaseLoader(only_cpu=False, hubert_path=None, rmvpe_path=None)
+
+title = "<center><strong><font size='7'>Vodex AI</font></strong></center>"
+theme = "aliabid94/new-theme"
+
+def find_files(directory):
+    file_paths = []
+    for filename in os.listdir(directory):
+        if filename.endswith('.pth') or filename.endswith('.zip') or filename.endswith('.index'):
+            file_paths.append(os.path.join(directory, filename))
+    return file_paths
+
+def unzip_in_folder(my_zip, my_dir):
+    with zipfile.ZipFile(my_zip) as zip:
+        for zip_info in zip.infolist():
+            if zip_info.is_dir():
+                continue
+            zip_info.filename = os.path.basename(zip_info.filename)
+            zip.extract(zip_info, my_dir)
+
+def find_my_model(a_, b_):
+    if a_ is None or a_.endswith(".pth"):
+        return a_, b_
+
+    txt_files = []
+    for base_file in [a_, b_]:
+        if base_file is not None and base_file.endswith(".txt"):
+            txt_files.append(base_file)
+
+    directory = os.path.dirname(a_)
+
+    for txt in txt_files:
+        with open(txt, 'r') as file:
+            first_line = file.readline()
+
+        download_manager(
+            url=first_line.strip(),
+            path=directory,
+            extension="",
+        )
+
+    for f in find_files(directory):
+        if f.endswith(".zip"):
+            unzip_in_folder(f, directory)
+
+    model = None
+    index = None
+    end_files = find_files(directory)
+
+    for ff in end_files:
+        if ff.endswith(".pth"):
+            model = os.path.join(directory, ff)
+            gr.Info(f"Model found: {ff}")
+        if ff.endswith(".index"):
+            index = os.path.join(directory, ff)
+            gr.Info(f"Index found: {ff}")
+
+    if not model:
+        gr.Error(f"Model not found in: {end_files}")
+
+    if not index:
+        gr.Warning("Index not found")
+
+    return model, index
+
+def get_file_size(url):
+    if "huggingface" not in url:
+        raise ValueError("Only downloads from Hugging Face are allowed")
+
+    try:
+        with urllib.request.urlopen(url) as response:
+            info = response.info()
+            content_length = info.get("Content-Length")
+
+        file_size = int(content_length)
+        if file_size > 500000000:
+            raise ValueError("The file is too large. You can only download files up to 500 MB in size.")
+
+    except Exception as e:
+        raise e
+
+def clear_files(directory):
+    time.sleep(15)
+    print(f"Clearing files: {directory}.")
+    shutil.rmtree(directory)
+
+def get_my_model(url_data):
+    if not url_data:
+        return None, None
+
+    if "," in url_data:
+        a_, b_ = url_data.split()
+        a_, b_ = a_.strip().replace("/blob/", "/resolve/"), b_.strip().replace("/blob/", "/resolve/")
+    else:
+        a_, b_ = url_data.strip().replace("/blob/", "/resolve/"), None
+
+    out_dir = "downloads"
+    folder_download = str(random.randint(1000, 9999))
+    directory = os.path.join(out_dir, folder_download)
+    os.makedirs(directory, exist_ok=True)
+
+    try:
+        get_file_size(a_)
+        if b_:
+            get_file_size(b_)
+
+        valid_url = [a_] if not b_ else [a_, b_]
+        for link in valid_url:
+            download_manager(
+                url=link,
+                path=directory,
+                extension="",
+            )
+
+        for f in find_files(directory):
+            if f.endswith(".zip"):
+                unzip_in_folder(f, directory)
+
+        model = None
+        index = None
+        end_files = find_files(directory)
+
+        for ff in end_files:
+            if ff.endswith(".pth"):
+                model = ff
+                gr.Info(f"Model found: {ff}")
+            if ff.endswith(".index"):
+                index = ff
+                gr.Info(f"Index found: {ff}")
+
+        if not model:
+            raise ValueError(f"Model not found in: {end_files}")
+
+        if not index:
+            gr.Warning("Index not found")
+        else:
+            index = os.path.abspath(index)
+
+        return os.path.abspath(model), index
+
+    except Exception as e:
+        raise e
+    finally:
+        t = threading.Thread(target=clear_files, args=(directory,))
+        t.start()
+
+def convert_now(audio_files, random_tag, converter):
+    return converter(
+        audio_files,
+        random_tag,
+        overwrite=False,
+        parallel_workers=8
+    )
+
+def apply_noisereduce(audio_list):
+    print("Applying noise reduction")
+
+    result = []
+    for audio_path in audio_list:
+        out_path = f'{os.path.splitext(audio_path)[0]}_noisereduce.wav'
+
+        try:
+            # Load audio file
+            audio = AudioSegment.from_file(audio_path)
+
+            # Convert audio to numpy array
+            samples = np.array(audio.get_array_of_samples())
+
+            # Reduce noise
+            reduced_noise = nr.reduce_noise(y=samples, sr=audio.frame_rate, prop_decrease=0.6)
+
+            # Convert reduced noise signal back to audio
+            reduced_audio = AudioSegment(
+                reduced_noise.tobytes(),
+                frame_rate=audio.frame_rate,
+                sample_width=audio.sample_width,
+                channels=audio.channels
+            )
+
+            # Save reduced audio to file
+            reduced_audio.export(out_path, format="wav")
+            result.append(out_path)
+
+        except Exception as e:
+            traceback.print_exc()
+            print(f"Error in noise reduction: {str(e)}")
+            result.append(audio_path)
+
+    return result
+
+def run(audio_files, file_m, file_index):
+    if not audio_files:
+        raise ValueError("Please provide an audio file.")
+
+    if isinstance(audio_files, str):
+        audio_files = [audio_files]
+
+    try:
+        duration_base = librosa.get_duration(filename=audio_files[0])
+        print("Duration:", duration_base)
+    except Exception as e:
+        print(e)
+
+    if file_m is not None and file_m.endswith(".txt"):
+        file_m, file_index = find_my_model(file_m, file_index)
+        print(file_m, file_index)
+
+    random_tag = "USER_" + str(random.randint(10000000, 99999999))
+
+    # Hardcoding pitch algorithm and other parameters
+    pitch_alg = "rmvpe+"
+    pitch_lvl = 0
+    index_inf = 0.75
+    r_m_f = 3
+    e_r = 0.25
+    c_b_p = 0.5
+
+    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,
+    )
+    time.sleep(0.1)
+
+    result = convert_now(audio_files, random_tag, converter)
+
+    # Always apply noise reduction
+    result = apply_noisereduce(result)
+
+    return result
+
+def model_conf():
+    model_files = [f for f in os.listdir("models") if f.endswith(".pth")]
+    return gr.Dropdown(
+        label="Select Model File",
+        choices=model_files,
+        value=model_files[0] if model_files else None,
+        interactive=True,
+    )
+
+def index_conf():
+    index_files = [f for f in os.listdir("models") if f.endswith(".index")]
+    return gr.Dropdown(
+        label="Select Index File",
+        choices=index_files,
+        value=index_files[0] if index_files else None,
+        interactive=True,
+    )
+
+def audio_conf():
+    return gr.File(
+        label="Audio files",
+        file_count="multiple",
+        type="filepath",
+        container=True,
+    )
+
+def button_conf():
+    return gr.Button(
+        "Inference",
+        variant="primary",
+    )
+
+def output_conf():
+    return gr.File(
+        label="Result",
+        file_count="multiple",
+        interactive=False,
+    )
+
+def get_gui(theme):
+    with gr.Blocks(theme=theme, delete_cache=(3200, 3200)) as app:
+        gr.Markdown(title)
+
+        aud = audio_conf()
+
+        model = model_conf()
+        indx = index_conf()
+        button_base = button_conf()
+        output_base = output_conf()
+
+        button_base.click(
+            run,
+            inputs=[
+                aud,
+                model,
+                indx,
+            ],
+            outputs=[output_base],
+        )
+
+        gr.Examples(
+            examples=[
+                [
+                    ["./test.ogg"],
+                    "./model.pth",
+                    "./model.index",
+                ],
+                [
+                    ["./example2/test2.ogg"],
+                    "./example2/model.pth",
+                    "./example2/model.index",
+                ],
+            ],
+            fn=run,
+            inputs=[
+                aud,
+                model,
+                indx,
+            ],
+            outputs=[output_base],
+            cache_examples=False,
+        )
+
+    return app
+
+if __name__ == "__main__":
+    app = get_gui(theme)
+    app.queue(default_concurrency_limit=40)
+    app.launch(
+        max_threads=40,
+        share=False,
+        show_error=True,
+        quiet=False,
+        debug=False,
+        allowed_paths=["./downloads/"],
+    )

example2/index_link.txt

@@ -0,0 +1 @@
+https://huggingface.co/sail-rvc/ayaka-jp/resolve/main/model.index?download=true

example2/model_link.txt

@@ -0,0 +1 @@
+https://huggingface.co/sail-rvc/ayaka-jp/resolve/main/model.pth?download=true

example3/zip_link.txt

@@ -0,0 +1 @@
+https://huggingface.co/Stevenojob/furina_JP/resolve/main/furina_jp.zip?download=true

gitattributes

@@ -0,0 +1,36 @@
+*.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
+model.index filter=lfs diff=lfs merge=lfs -text

model.index

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af434a9142b070f7091dcdbbf957b7a01bbc96294add99d186ef1e0d4b226eac
+size 83987395

model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:896fcee182ecdcea6645a691366ac50153bc63015f43c981da135a8cabe2f088
+size 55028048

models/metadata.json

@@ -0,0 +1,152 @@
+{
+  "title": "US Ascent",
+  "author": {
+    "name": "mayank dubey",
+    "discordUserId": null
+  },
+  "md5": "b0a77398fc88806fda285f4ecd6a5839",
+  "uploadedAt": "2024-07-05T07:38:18.500Z",
+  "weightsLink": "https://www.weights.gg/models/cly8dvwn8000cagr4ohpzo4q2",
+  "id": "cly8dvwn8000cagr4ohpzo4q2",
+  "type": "v2",
+  "tags": [],
+  "description": "US Ascent",
+  "samples": [],
+  "files": [
+    {
+      "name": "model.index",
+      "size": 101587779,
+      "md5": "61a545d9b5bb380bed408a51708b210e"
+    },
+    {
+      "name": "model.pth",
+      "size": 57577722,
+      "md5": "b0a77398fc88806fda285f4ecd6a5839"
+    }
+  ],
+  "torchMetadata": {
+    "config": {
+      "spec_channels": 1025,
+      "segment_size": 32,
+      "inter_channels": 192,
+      "hidden_channels": 192,
+      "filter_channels": 768,
+      "n_heads": 2,
+      "n_layers": 6,
+      "kernel_size": 3,
+      "p_dropout": 0,
+      "resblock": "1",
+      "resblock_kernel_sizes": [
+        3,
+        7,
+        11
+      ],
+      "resblock_dilation_sizes": [
+        [
+          1,
+          3,
+          5
+        ],
+        [
+          1,
+          3,
+          5
+        ],
+        [
+          1,
+          3,
+          5
+        ]
+      ],
+      "upsample_rates": [
+        12,
+        10,
+        2,
+        2
+      ],
+      "upsample_initial_channel": 512,
+      "upsample_kernel_sizes": [
+        24,
+        20,
+        4,
+        4
+      ],
+      "emb_channels": null,
+      "spk_embed_dim": 109,
+      "gin_channels": 256,
+      "sr": 48000
+    },
+    "f0": 1,
+    "version": "v2",
+    "extra_info": {
+      "config": [
+        1025,
+        32,
+        192,
+        192,
+        768,
+        2,
+        6,
+        3,
+        0,
+        "1",
+        [
+          3,
+          7,
+          11
+        ],
+        [
+          [
+            1,
+            3,
+            5
+          ],
+          [
+            1,
+            3,
+            5
+          ],
+          [
+            1,
+            3,
+            5
+          ]
+        ],
+        [
+          12,
+          10,
+          2,
+          2
+        ],
+        512,
+        [
+          24,
+          20,
+          4,
+          4
+        ],
+        109,
+        256,
+        48000
+      ],
+      "epoch": 233,
+      "step": 6291,
+      "sr": 48000,
+      "f0": 1,
+      "version": "v2",
+      "creation_date": "2024-07-05T07:01:09.035229",
+      "model_hash": "7c335d1650be63dea6409d741859c137dc6827d9945d6afba08867ab4281e056"
+    },
+    "epochs": 233,
+    "step": 6291,
+    "creation_date": "2024-07-05T07:01:09.035229",
+    "model_hash": "7c335d1650be63dea6409d741859c137dc6827d9945d6afba08867ab4281e056"
+  },
+  "url": "https://models.weights.gg/cly79hr6d1211hlpr4obj48ab.zip",
+  "urls": [],
+  "epochs": 233,
+  "originalFileList": [
+    "model.index",
+    "model.pth"
+  ]
+}

models/model.index

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9cc11461add817f1964dfac11c37033a20037d28fe2935038d884196f556590
+size 101587779

models/model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:595287a521b83cbd8cf8372e1a8c3200081e88ce8c0b7866ebc9db7e66be9512
+size 57577722

packages.txt

@@ -0,0 +1 @@
+ffmpeg

requirements.txt

@@ -0,0 +1,6 @@
+torch==2.2.0
+infer-rvc-python==1.1.0
+edge-tts
+pedalboard
+noisereduce
+numpy==1.23.5