deploy: b064586

_sources/separation/singing-voice-extraction.ipynb

@@ -85,16 +85,36 @@
    "outputs": [],
    "source": [
     "# Importing and initializing a melodia instance\n",
-    "from compiam import load_model\n",
+    "import soundfile as sf\n",
+    "from compiam import load_model, load_dataset\n",
     "separation_model = load_model('separation:cold-diff-sep')\n",
     "\n",
-    "# Running extraction for an example track\n",
+    "# Loading an normalizing an example track\n",
+    "saraga_carnatic = load_dataset(\n",
+    "    \"saraga_carnatic\",\n",
+    "    data_home=os.path.join(\"..\", \"audio\", \"mir_datasets\")\n",
+    ")\n",
+    "saraga_tracks = saraga_carnatic.load_tracks()\n",
+    "example = saraga_tracks[\"109_Sri_Raghuvara_Sugunaalaya\"]\n",
+    "input_mixture, sr = sf.read(example.audio_path)\n",
+    "\n",
+    "input_mixture = input_mixture.T\n",
+    "mean = np.mean(input_mixture, keepdims=True)\n",
+    "std = np.std(input_mixture, keepdims=True)\n",
+    "input_mixture = (input_mixture - mean) / (1e-6 + std)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "### Getting 30 seconds and separating\n",
+    "input_mixture = input_mixture[:, :44100*30]\n",
     "separation = separation_model.separate(\n",
-    "    input_data=os.path.join(\n",
-    "        \"..\", \"audio\", \"mir_datasets\", \"saraga1.5_carnatic\",\n",
-    "        \"Live at Vani Mahal by Sanjay Subrahmanyan\", \"Sri Raghuvara Sugunaalaya\",\n",
-    "        \"Sanjay Subrahmanyan - Sri Raghuvara Sugunaalaya.mp3\"\n",
-    "    ),\n",
+    "    input_data=input_mixture,\n",
+    "    input_sr=sr\n",
     ")"
    ]
   },
@@ -109,7 +129,7 @@
     "# And we play it!\n",
     "ipd.Audio(\n",
     "    data=separation,\n",
-    "    rate=22050,\n",
+    "    rate=separation_model.sample_rate,\n",
     ")"
    ]
   }

melodic_analysis/exploring-raga.html

@@ -1432,14 +1432,14 @@ <h3>3.1 Predominant pitch extraction<a class="headerlink" href="#predominant-pit
 </div>
 </div>
 <div class="cell_output docutils container">
-<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>2023-11-29 22:48:31.864978: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library &#39;libcudart.so.11.0&#39;; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /opt/hostedtoolcache/Python/3.8.18/x64/lib/python3.8/site-packages/cv2/../../lib64:
-2023-11-29 22:48:31.865007: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
+<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>2023-11-30 11:53:38.008753: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library &#39;libcudart.so.11.0&#39;; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /opt/hostedtoolcache/Python/3.8.18/x64/lib/python3.8/site-packages/cv2/../../lib64:
+2023-11-30 11:53:38.008780: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
 </pre></div>
 </div>
-<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>2023-11-29 22:48:33.012095: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library &#39;libcuda.so.1&#39;; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /opt/hostedtoolcache/Python/3.8.18/x64/lib/python3.8/site-packages/cv2/../../lib64:
-2023-11-29 22:48:33.012123: W tensorflow/stream_executor/cuda/cuda_driver.cc:269] failed call to cuInit: UNKNOWN ERROR (303)
-2023-11-29 22:48:33.012148: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (fv-az1247-986): /proc/driver/nvidia/version does not exist
-2023-11-29 22:48:33.012329: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 FMA
+<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>2023-11-30 11:53:39.158627: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library &#39;libcuda.so.1&#39;; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /opt/hostedtoolcache/Python/3.8.18/x64/lib/python3.8/site-packages/cv2/../../lib64:
+2023-11-30 11:53:39.158653: W tensorflow/stream_executor/cuda/cuda_driver.cc:269] failed call to cuInit: UNKNOWN ERROR (303)
+2023-11-30 11:53:39.158679: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (fv-az888-914): /proc/driver/nvidia/version does not exist
+2023-11-30 11:53:39.158847: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 FMA
 To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
 </pre></div>
 </div>
@@ -1727,31 +1727,11 @@ <h3>3.2 Visualising predominant pitch<a class="headerlink" href="#visualising-pr
 </div>
 </div>
 <div class="cell_output docutils container">
-<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>{54.997834212038505: &#39;R2&#39;,
- 109.99566842407701: &#39;R2&#39;,
- 219.99133684815402: &#39;R2&#39;,
- 439.98267369630804: &#39;R2&#39;,
- 879.965347392616: &#39;R2&#39;,
- 58.268175617345825: &#39;G2&#39;,
+<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>{58.268175617345825: &#39;G2&#39;,
  116.53635123469165: &#39;G2&#39;,
  233.0727024693833: &#39;G2&#39;,
  466.1454049387666: &#39;G2&#39;,
  932.2908098775332: &#39;G2&#39;,
- 82.40364421278775: &#39;D2&#39;,
- 164.8072884255755: &#39;D2&#39;,
- 329.614576851151: &#39;D2&#39;,
- 659.229153702302: &#39;D2&#39;,
- 1318.458307404604: &#39;D2&#39;,
- 65.40381575469627: &#39;M1&#39;,
- 130.80763150939254: &#39;M1&#39;,
- 261.6152630187851: &#39;M1&#39;,
- 523.2305260375701: &#39;M1&#39;,
- 1046.46105207514: &#39;M1&#39;,
- 73.4133009992652: &#39;P&#39;,
- 146.8266019985304: &#39;P&#39;,
- 293.6532039970608: &#39;P&#39;,
- 587.3064079941216: &#39;P&#39;,
- 1174.6128159882435: &#39;P&#39;,
  87.30361988416256: &#39;N2&#39;,
  174.60723976832512: &#39;N2&#39;,
  349.21447953665023: &#39;N2&#39;,
@@ -1761,7 +1741,27 @@ <h3>3.2 Visualising predominant pitch<a class="headerlink" href="#visualising-pr
  97.995: &#39;S&#39;,
  195.99: &#39;S&#39;,
  391.98: &#39;S&#39;,
- 783.96: &#39;S&#39;}
+ 783.96: &#39;S&#39;,
+ 54.997834212038505: &#39;R2&#39;,
+ 109.99566842407701: &#39;R2&#39;,
+ 219.99133684815402: &#39;R2&#39;,
+ 439.98267369630804: &#39;R2&#39;,
+ 879.965347392616: &#39;R2&#39;,
+ 73.4133009992652: &#39;P&#39;,
+ 146.8266019985304: &#39;P&#39;,
+ 293.6532039970608: &#39;P&#39;,
+ 587.3064079941216: &#39;P&#39;,
+ 1174.6128159882435: &#39;P&#39;,
+ 65.40381575469627: &#39;M1&#39;,
+ 130.80763150939254: &#39;M1&#39;,
+ 261.6152630187851: &#39;M1&#39;,
+ 523.2305260375701: &#39;M1&#39;,
+ 1046.46105207514: &#39;M1&#39;,
+ 82.40364421278775: &#39;D2&#39;,
+ 164.8072884255755: &#39;D2&#39;,
+ 329.614576851151: &#39;D2&#39;,
+ 659.229153702302: &#39;D2&#39;,
+ 1318.458307404604: &#39;D2&#39;}
 </pre></div>
 </div>
 </div>
@@ -2200,7 +2200,7 @@ <h4>Fixing tonic errors in folded plots<a class="headerlink" href="#fixing-tonic
 </div>
 </div>
 <div class="cell_output docutils container">
-<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[&lt;matplotlib.lines.Line2D at 0x7f5dcda43d00&gt;]
+<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[&lt;matplotlib.lines.Line2D at 0x7f1579aca220&gt;]
 </pre></div>
 </div>
 <img alt="../_images/exploring-raga_110_1.png" src="../_images/exploring-raga_110_1.png" />
@@ -2317,7 +2317,7 @@ <h4>Fixing tonic errors in folded plots<a class="headerlink" href="#fixing-tonic
 </div>
 </div>
 <div class="cell_output docutils container">
-<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[&lt;matplotlib.lines.Line2D at 0x7f5dcda3ea00&gt;]
+<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[&lt;matplotlib.lines.Line2D at 0x7f1579abedf0&gt;]
 </pre></div>
 </div>
 <img alt="../_images/exploring-raga_120_1.png" src="../_images/exploring-raga_120_1.png" />
@@ -2666,8 +2666,8 @@ <h3>3.5 Pitch density across rāga<a class="headerlink" href="#pitch-density-acr
 </div>
 </div>
 <div class="cell_output docutils container">
-<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Rītigauḷa: {&#39;R2&#39;, &#39;G2&#39;, &#39;D2&#39;, &#39;M1&#39;, &#39;P&#39;, &#39;N2&#39;, &#39;S&#39;}
-Bhairavi: {&#39;R2&#39;, &#39;D1&#39;, &#39;G2&#39;, &#39;D2&#39;, &#39;M1&#39;, &#39;P&#39;, &#39;N2&#39;, &#39;S&#39;}
+<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Rītigauḷa: {&#39;G2&#39;, &#39;N2&#39;, &#39;S&#39;, &#39;R2&#39;, &#39;P&#39;, &#39;M1&#39;, &#39;D2&#39;}
+Bhairavi: {&#39;G2&#39;, &#39;N2&#39;, &#39;S&#39;, &#39;R2&#39;, &#39;P&#39;, &#39;D2&#39;, &#39;M1&#39;, &#39;D1&#39;}
 </pre></div>
 </div>
 </div>

melodic_analysis/raga-recognition.html

@@ -623,25 +623,16 @@ <h2> Contents </h2>
 <div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>  0%|          | 0.00/20.4M [00:00&lt;?, ?B/s]
 </pre></div>
 </div>
-<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>  5%|▌         | 1.05M/20.4M [00:00&lt;00:02, 9.12MB/s]
+<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span> 23%|██▎       | 4.72M/20.4M [00:00&lt;00:00, 20.5MB/s]
 </pre></div>
 </div>
-<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span> 23%|██▎       | 4.72M/20.4M [00:00&lt;00:01, 15.4MB/s]
+<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>100%|██████████| 20.4M/20.4M [00:00&lt;00:00, 67.6MB/s]
 </pre></div>
 </div>
-<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span> 44%|████▎     | 8.91M/20.4M [00:00&lt;00:01, 10.2MB/s]
+<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>
 </pre></div>
 </div>
-<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span> 54%|█████▍    | 11.0M/20.4M [00:01&lt;00:01, 8.46MB/s]
-</pre></div>
-</div>
-<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span> 85%|████████▍ | 17.3M/20.4M [00:01&lt;00:00, 13.4MB/s]
-</pre></div>
-</div>
-<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>100%|██████████| 20.4M/20.4M [00:01&lt;00:00, 14.1MB/s]
-</pre></div>
-</div>
-<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[2023-11-29 22:50:07,412] WARNING [compiam.melody.raga_recognition.deepsrgm.download_model:155] Files downloaded and extracted successfully.
+<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[2023-11-30 11:55:08,924] WARNING [compiam.melody.raga_recognition.deepsrgm.download_model:155] Files downloaded and extracted successfully.
 </pre></div>
 </div>
 </div>