Duplicate from PierreHanna/AudioSimilarity

.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
+*.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
+index.filenames filter=lfs diff=lfs merge=lfs -text
+index.index filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: AudioSimilarity
+emoji: 🐢
+colorFrom: green
+colorTo: blue
+sdk: gradio
+sdk_version: 3.28.0
+app_file: app.py
+pinned: false
+duplicated_from: PierreHanna/AudioSimilarity
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,106 @@
+import time
+import json
+import os
+import openl3
+import librosa
+import pickle
+import gradio as gr
+import numpy as np
+import faiss
+from pytube import YouTube
+
+embed_html1 = '<iframe width="560" height="315" src="https://www.youtube.com/embed/'
+embed_html2 = '" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>'
+
+
+def download_audio(id_video):
+    video = YouTube(id_video,use_oauth=True, allow_oauth_cache=True)
+    id = id_video.split("?v=")[-1][:11]
+    print("ID youtube ", id)
+    audio_streams = video.streams.filter(only_audio=True)
+    audio_stream = audio_streams[0]
+    audio_file = audio_stream.download()
+    audio_parts = audio_file.split('/')[-1]
+    audio_title = '.'.join(audio_parts.split('.')[:-1])
+    embed_html_all = embed_html1 + id +embed_html2
+    return audio_file, audio_file, embed_html_all
+
+def process_url(input_path):
+    # setup the client
+    audio_file, audio_file, embed_html_all = download_audio(input_path)
+    return process(audio_file, embed_html_all)
+
+def process_file(input_path):
+    return process(input_path, '')
+
+def process(audio_file, embed_html_all):
+    model = openl3.models.load_audio_embedding_model(input_repr="linear", content_type="music",embedding_size=512)
+    audio, sr = librosa.load(audio_file, mono=True)
+    emb, ts = openl3.get_audio_embedding(audio, sr, model=model)  
+    emb = np.mean(emb, axis=0)
+    print("SHAPE ", emb.shape)
+    
+    ind = faiss.read_index("index.index")
+    ind_filenames = pickle.load(open('index.filenames','rb'))
+    dict_bmg = pickle.load(open('dict_bmg.pickle','rb')) # filename to url
+    D, I = ind.search(emb.reshape((1,512)), 5) 
+
+    top1 = dict_bmg[ind_filenames[I[0][0]]]
+    top2 = dict_bmg[ind_filenames[I[0][1]]]
+    top3 = dict_bmg[ind_filenames[I[0][2]]]
+    top4 = dict_bmg[ind_filenames[I[0][3]]]
+    top5 = dict_bmg[ind_filenames[I[0][4]]]
+    
+    return top1, top2, top3, top4, top5
+            
+ 
+with gr.Blocks() as demo:
+    
+    with gr.Row():
+
+        with gr.Column():
+
+            with gr.Row():
+                #gr.HTML(embed_html)
+                html = gr.HTML()
+            
+            with gr.Row():
+                with gr.Column():
+                    audio_url_input = gr.Textbox(placeholder='YouTube video URL', label='YouTube video URL')
+                    analyze_url_btn = gr.Button('Search from URL')
+
+            with gr.Row():
+                with gr.Column():
+                    audio_input_file = gr.Audio(type="filepath", label='Audio Input')
+                    analyze_file_btn = gr.Button('Search from file')
+                
+
+            with gr.Row():
+                with gr.Column():
+                    '''
+                    gr.HTML("<h3>Top 1</h3>")
+                    top1 = gr.Textbox(label="top1", show_label=False)
+                    gr.HTML("<h3>Top 2</h3>")
+                    top2 = gr.Textbox(label="top2", show_label=False)
+                    gr.HTML("<h3>Top 3</h3>")
+                    top3 = gr.Textbox(label="top3", show_label=False)
+                    gr.HTML("<h3>Top 4</h3>")
+                    top4 = gr.Textbox(label="top4", show_label=False)
+                    gr.HTML("<h3>Top 5</h3>")
+                    top5 = gr.Textbox(label="top5", show_label=False)
+                    '''
+                    top1 = gr.Audio(label="top1", show_label=True)
+                    top2 = gr.Audio(label="top2", show_label=True)
+                    top3 = gr.Audio(label="top3", show_label=True)
+                    top4 = gr.Audio(label="top4", show_label=True)
+                    top5 = gr.Audio(label="top5", show_label=True)
+            
+    
+    analyze_url_btn.click(process_url, inputs=[audio_url_input], 
+                      outputs=[top1, top2, top3, top4, top5])
+
+    analyze_file_btn.click(process_file, inputs=[audio_input_file], 
+                      outputs=[top1, top2, top3, top4, top5])
+
+
+demo.launch(debug=True)

dict_bmg.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e67645329cc091ba56c358ba3dc61032a457878f3b879f0e2e720294d5337b1
+size 15953609

index.filenames

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d4b8ec64b35965b7ca3d202d767f4c9549934683bf1b854a2efc4aa12d1634d
+size 1987986

index.index

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8db1af12dc9323081564f89052ea8cd331a826b5066ec6bbe8943b8b5c7f094b
+size 117442605

requirements.txt

@@ -0,0 +1,4 @@
+pytube
+faiss-cpu
+librosa
+openl3