Update app.py

app.py

@@ -1,360 +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/"],
-    )
+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/"],
+    )