added spleeter code

.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
+pretrained_models filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,12 @@
+---
+title: Rvc Spleeter Voice
+emoji: 🌍
+colorFrom: indigo
+colorTo: green
+sdk: gradio
+sdk_version: 4.36.1
+app_file: app.py
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,87 @@
+from spleeter.separator import Separator
+import gradio as gr
+import shutil
+import librosa
+import soundfile
+import os
+from gradio_client import Client, file
+import subprocess
+
+try:
+  shutil.rmtree("output")
+except FileNotFoundError:
+  pass
+
+
+def spleeter(aud, model_file, index_file, pitch):
+  separator = Separator('spleeter:2stems')
+  filename = os.path.basename(aud).split('.')[0]
+  accompaniment_filename = f"./output/audio_example/{filename}_accompaniment.wav"
+  vocal_filename = f"./output/audio_example/{filename}_vocals.wav"
+  song_filename = f'./output/audio_example/{filename}_song.wav'
+
+  separator.separate_to_file(aud, "output/", filename_format="audio_example/%s_{instrument}.wav" % filename)
+
+  # change pitch
+  y, sr = librosa.load(accompaniment_filename)
+  new_accompaniment = librosa.effects.pitch_shift(y, sr, pitch)
+  soundfile.write(accompaniment_filename, new_accompaniment, sr, )
+
+  # send vocal for processing
+  # https://huggingface.co/spaces/r3gm/rvc_zero
+  client = Client("r3gm/rvc_zero")
+  result = client.predict(
+    audio_files=[file(vocal_filename)],
+    file_m=file(model_file),
+    pitch_alg="rmvpe+",
+    pitch_lvl=pitch,
+    file_index=file(index_file),
+    index_inf=0.75,
+    r_m_f=3,
+    e_r=0.25,
+    c_b_p=0.5,
+    active_noise_reduce=False,
+    audio_effects=False,
+    api_name="/run"
+  )[0]
+
+  # combine accompaniment and vocal
+  command = f"""ffmpeg -i "{result}" -i "{accompaniment_filename}" -filter_complex amix=inputs=2:duration=longest "{song_filename}" """
+  subprocess.call(command, shell=True)
+
+  return song_filename
+
+inputs = [
+          gr.Audio(sources='upload', label="Input Audio File", type="filepath"),
+gr.File(
+        label="Model file",
+        type="filepath",
+        height=130,
+    ),
+gr.File(
+        label="Index file",
+        type="filepath",
+        height=130,
+    ),
+gr.Slider(
+        label="Pitch level",
+        minimum=-24,
+        maximum=24,
+        step=1,
+        value=0,
+        visible=True,
+        interactive=True,
+    )
+]
+outputs =  [
+  gr.Audio(label="Output Audio", type="filepath"),
+]
+
+title = "Music Spleeter"
+description = "Clearing a musical composition of the performer's voice is a common task. It is solved well, for example, by professional audio file editing programs. AI algorithms have also been gaining ground recently."
+article = "<div style='text-align: center; max-width:800px; margin:10px auto;'><p>In this case we use Deezer's Spleeter with ready pretrained models. It can leave as an output both just the music and just the performer's voice.</p><p>Sources: <a href='https://github.com/deezer/spleeter/' target='_blank'>Spleeter</a>: a Fast and Efficient Music Source Separation Tool with Pre-Trained Models</p><p style='text-align: center'><a href='https://starstat.yt/cat/music' target='_blank'>StarStat Music</a>: Youtubers Net Worth in category Music</p></div>"
+
+
+if __name__ == '__main__':
+  gr.Interface(spleeter, inputs, outputs).launch()
+

main.py

@@ -0,0 +1,17 @@
+from gradio_client import Client, file
+
+client = Client("r3gm/rvc_zero")
+result = client.predict(
+		audio_files=[file('https://github.com/gradio-app/gradio/raw/main/test/test_files/sample_file.pdf')],
+		file_m=file('https://github.com/gradio-app/gradio/raw/main/test/test_files/sample_file.pdf'),
+		pitch_alg="rmvpe+",
+		pitch_lvl=0,
+		file_index=file('https://github.com/gradio-app/gradio/raw/main/test/test_files/sample_file.pdf'),
+		index_inf=0.75,
+		r_m_f=3,
+		e_r=0.25,
+		c_b_p=0.5,
+		active_noise_reduce=False,
+		audio_effects=False,
+		api_name="/run"
+)