philschmid
/

pyannote-speaker-diarization-endpoint

+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 1. Setup & Installation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Overwriting requirements.txt\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%writefile requirements.txt\n",
+    "torchaudio\n",
+    "pyannote.audio"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Collecting torchaudio\n",
+      "  Downloading torchaudio-0.12.1-cp39-cp39-manylinux1_x86_64.whl (3.7 MB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.7/3.7 MB\u001b[0m \u001b[31m95.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m\n",
+      "\u001b[?25hCollecting pyannote.audio\n",
+      "  Downloading pyannote.audio-2.0.1-py2.py3-none-any.whl (385 kB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m385.9/385.9 kB\u001b[0m \u001b[31m47.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+      "\u001b[?25hCollecting torch==1.12.1\n",
+      "  Using cached torch-1.12.1-cp39-cp39-manylinux1_x86_64.whl (776.4 MB)\n",
+      "Requirement already satisfied: typing-extensions in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from torch==1.12.1->torchaudio->-r requirements.txt (line 1)) (4.3.0)\n",
+      "Collecting pytorch-lightning<1.7,>=1.5.4\n",
+      "  Downloading pytorch_lightning-1.6.5-py3-none-any.whl (585 kB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m585.9/585.9 kB\u001b[0m \u001b[31m56.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+      "\u001b[?25hCollecting hmmlearn<0.3,>=0.2.7\n",
+      "  Downloading hmmlearn-0.2.8-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.whl (217 kB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m217.2/217.2 kB\u001b[0m \u001b[31m22.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+      "\u001b[?25hCollecting torch-audiomentations>=0.11.0\n",
+      "  Downloading torch_audiomentations-0.11.0-py3-none-any.whl (47 kB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m47.9/47.9 kB\u001b[0m \u001b[31m5.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+      "\u001b[?25hCollecting speechbrain<0.6,>=0.5.12\n",
+      "  Downloading speechbrain-0.5.13-py3-none-any.whl (498 kB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m499.0/499.0 kB\u001b[0m \u001b[31m56.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+      "\u001b[?25hCollecting singledispatchmethod\n",
+      "  Downloading singledispatchmethod-1.0-py2.py3-none-any.whl (4.7 kB)\n",
+      "Collecting torchmetrics<1.0,>=0.6\n",
+      "  Downloading torchmetrics-0.10.0-py3-none-any.whl (529 kB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m529.2/529.2 kB\u001b[0m \u001b[31m49.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+      "\u001b[?25hCollecting pyannote.pipeline<3.0,>=2.3\n",
+      "  Downloading pyannote.pipeline-2.3-py3-none-any.whl (30 kB)\n",
+      "Collecting pyannote.metrics<4.0,>=3.2\n",
+      "  Downloading pyannote.metrics-3.2.1-py3-none-any.whl (51 kB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m51.4/51.4 kB\u001b[0m \u001b[31m4.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+      "\u001b[?25hCollecting backports.cached-property\n",
+      "  Downloading backports.cached_property-1.0.2-py3-none-any.whl (6.1 kB)\n",
+      "Collecting pytorch-metric-learning<2.0,>=1.0.0\n",
+      "  Downloading pytorch_metric_learning-1.6.2-py3-none-any.whl (111 kB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m111.4/111.4 kB\u001b[0m \u001b[31m18.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+      "\u001b[?25hCollecting networkx<3.0,>=2.6\n",
+      "  Downloading networkx-2.8.7-py3-none-any.whl (2.0 MB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━��━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.0/2.0 MB\u001b[0m \u001b[31m73.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+      "\u001b[?25hCollecting omegaconf<3.0,>=2.1\n",
+      "  Downloading omegaconf-2.2.3-py3-none-any.whl (79 kB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m79.3/79.3 kB\u001b[0m \u001b[31m7.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+      "\u001b[?25hCollecting asteroid-filterbanks<0.5,>=0.4\n",
+      "  Downloading asteroid_filterbanks-0.4.0-py3-none-any.whl (29 kB)\n",
+      "Collecting huggingface-hub<0.9,>=0.7\n",
+      "  Using cached huggingface_hub-0.8.1-py3-none-any.whl (101 kB)\n",
+      "Requirement already satisfied: soundfile<0.11,>=0.10.2 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from pyannote.audio->-r requirements.txt (line 2)) (0.10.3.post1)\n",
+      "Collecting einops<0.4.0,>=0.3\n",
+      "  Downloading einops-0.3.2-py3-none-any.whl (25 kB)\n",
+      "Collecting pyannote.core<5.0,>=4.4\n",
+      "  Downloading pyannote.core-4.5-py3-none-any.whl (60 kB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m60.5/60.5 kB\u001b[0m \u001b[31m8.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+      "\u001b[?25hCollecting pyannote.database<5.0,>=4.1.1\n",
+      "  Downloading pyannote.database-4.1.3-py3-none-any.whl (41 kB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m41.6/41.6 kB\u001b[0m \u001b[31m4.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+      "\u001b[?25hCollecting semver<3.0,>=2.10.2\n",
+      "  Downloading semver-2.13.0-py2.py3-none-any.whl (12 kB)\n",
+      "Requirement already satisfied: numpy in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from asteroid-filterbanks<0.5,>=0.4->pyannote.audio->-r requirements.txt (line 2)) (1.22.4)\n",
+      "Requirement already satisfied: scipy>=0.19 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from hmmlearn<0.3,>=0.2.7->pyannote.audio->-r requirements.txt (line 2)) (1.9.0)\n",
+      "Requirement already satisfied: scikit-learn>=0.16 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from hmmlearn<0.3,>=0.2.7->pyannote.audio->-r requirements.txt (line 2)) (1.1.2)\n",
+      "Requirement already satisfied: requests in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from huggingface-hub<0.9,>=0.7->pyannote.audio->-r requirements.txt (line 2)) (2.28.1)\n",
+      "Requirement already satisfied: tqdm in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from huggingface-hub<0.9,>=0.7->pyannote.audio->-r requirements.txt (line 2)) (4.64.0)\n",
+      "Requirement already satisfied: filelock in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from huggingface-hub<0.9,>=0.7->pyannote.audio->-r requirements.txt (line 2)) (3.8.0)\n",
+      "Requirement already satisfied: packaging>=20.9 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from huggingface-hub<0.9,>=0.7->pyannote.audio->-r requirements.txt (line 2)) (21.3)\n",
+      "Requirement already satisfied: pyyaml>=5.1 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from huggingface-hub<0.9,>=0.7->pyannote.audio->-r requirements.txt (line 2)) (6.0)\n",
+      "Collecting antlr4-python3-runtime==4.9.*\n",
+      "  Downloading antlr4-python3-runtime-4.9.3.tar.gz (117 kB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m117.0/117.0 kB\u001b[0m \u001b[31m14.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+      "\u001b[?25h  Preparing metadata (setup.py) ... \u001b[?25ldone\n",
+      "\u001b[?25hRequirement already satisfied: sortedcontainers>=2.0.4 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from pyannote.core<5.0,>=4.4->pyannote.audio->-r requirements.txt (line 2)) (2.4.0)\n",
+      "Collecting simplejson>=3.8.1\n",
+      "  Downloading simplejson-3.17.6-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl (136 kB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m136.6/136.6 kB\u001b[0m \u001b[31m17.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+      "\u001b[?25hRequirement already satisfied: pandas>=0.19 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from pyannote.database<5.0,>=4.1.1->pyannote.audio->-r requirements.txt (line 2)) (1.4.3)\n",
+      "Collecting typer[all]>=0.2.1\n",
+      "  Downloading typer-0.6.1-py3-none-any.whl (38 kB)\n",
+      "Collecting matplotlib>=2.0.0\n",
+      "  Downloading matplotlib-3.6.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (11.8 MB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m11.8/11.8 MB\u001b[0m \u001b[31m72.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
+      "\u001b[?25hRequirement already satisfied: tabulate>=0.7.7 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from pyannote.metrics<4.0,>=3.2->pyannote.audio->-r requirements.txt (line 2)) (0.8.10)\n",
+      "Collecting docopt>=0.6.2\n",
+      "  Downloading docopt-0.6.2.tar.gz (25 kB)\n",
+      "  Preparing metadata (setup.py) ... \u001b[?25ldone\n",
+      "\u001b[?25hRequirement already satisfied: sympy>=1.1 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from pyannote.metrics<4.0,>=3.2->pyannote.audio->-r requirements.txt (line 2)) (1.11.1)\n",
+      "Collecting optuna>=1.4\n",
+      "  Downloading optuna-3.0.2-py3-none-any.whl (348 kB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m348.3/348.3 kB\u001b[0m \u001b[31m27.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+      "\u001b[?25hRequirement already satisfied: protobuf<=3.20.1 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from pytorch-lightning<1.7,>=1.5.4->pyannote.audio->-r requirements.txt (line 2)) (3.19.4)\n",
+      "Requirement already satisfied: tensorboard>=2.2.0 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from pytorch-lightning<1.7,>=1.5.4->pyannote.audio->-r requirements.txt (line 2)) (2.10.0)\n",
+      "Collecting pyDeprecate>=0.3.1\n",
+      "  Downloading pyDeprecate-0.3.2-py3-none-any.whl (10 kB)\n",
+      "Requirement already satisfied: fsspec[http]!=2021.06.0,>=2021.05.0 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from pytorch-lightning<1.7,>=1.5.4->pyannote.audio->-r requirements.txt (line 2)) (2022.7.1)\n",
+      "Requirement already satisfied: torchvision in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from pytorch-metric-learning<2.0,>=1.0.0->pyannote.audio->-r requirements.txt (line 2)) (0.12.0+cu113)\n",
+      "Requirement already satisfied: cffi>=1.0 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from soundfile<0.11,>=0.10.2->pyannote.audio->-r requirements.txt (line 2)) (1.15.1)\n",
+      "Requirement already satisfied: joblib in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from speechbrain<0.6,>=0.5.12->pyannote.audio->-r requirements.txt (line 2)) (1.1.0)\n",
+      "Requirement already satisfied: sentencepiece in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from speechbrain<0.6,>=0.5.12->pyannote.audio->-r requirements.txt (line 2)) (0.1.97)\n",
+      "Collecting hyperpyyaml\n",
+      "  Downloading HyperPyYAML-1.0.1.tar.gz (14 kB)\n",
+      "  Preparing metadata (setup.py) ... \u001b[?25ldone\n",
+      "\u001b[?25hCollecting torch-pitch-shift>=1.2.2\n",
+      "  Downloading torch_pitch_shift-1.2.2-py3-none-any.whl (5.0 kB)\n",
+      "Requirement already satisfied: librosa>=0.6.0 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from torch-audiomentations>=0.11.0->pyannote.audio->-r requirements.txt (line 2)) (0.9.2)\n",
+      "Collecting julius<0.3,>=0.2.3\n",
+      "  Downloading julius-0.2.7.tar.gz (59 kB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m59.6/59.6 kB\u001b[0m \u001b[31m4.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+      "\u001b[?25h  Preparing metadata (setup.py) ... \u001b[?25ldone\n",
+      "\u001b[?25hRequirement already satisfied: pycparser in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from cffi>=1.0->soundfile<0.11,>=0.10.2->pyannote.audio->-r requirements.txt (line 2)) (2.21)\n",
+      "Requirement already satisfied: aiohttp in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from fsspec[http]!=2021.06.0,>=2021.05.0->pytorch-lightning<1.7,>=1.5.4->pyannote.audio->-r requirements.txt (line 2)) (3.8.1)\n",
+      "Requirement already satisfied: pooch>=1.0 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from librosa>=0.6.0->torch-audiomentations>=0.11.0->pyannote.audio->-r requirements.txt (line 2)) (1.6.0)\n",
+      "Requirement already satisfied: numba>=0.45.1 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from librosa>=0.6.0->torch-audiomentations>=0.11.0->pyannote.audio->-r requirements.txt (line 2)) (0.56.0)\n",
+      "Requirement already satisfied: resampy>=0.2.2 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from librosa>=0.6.0->torch-audiomentations>=0.11.0->pyannote.audio->-r requirements.txt (line 2)) (0.4.0)\n",
+      "Requirement already satisfied: audioread>=2.1.9 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from librosa>=0.6.0->torch-audiomentations>=0.11.0->pyannote.audio->-r requirements.txt (line 2)) (3.0.0)\n",
+      "Requirement already satisfied: decorator>=4.0.10 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from librosa>=0.6.0->torch-audiomentations>=0.11.0->pyannote.audio->-r requirements.txt (line 2)) (5.1.1)\n",
+      "Collecting cycler>=0.10\n",
+      "  Downloading cycler-0.11.0-py3-none-any.whl (6.4 kB)\n",
+      "Requirement already satisfied: python-dateutil>=2.7 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from matplotlib>=2.0.0->pyannote.metrics<4.0,>=3.2->pyannote.audio->-r requirements.txt (line 2)) (2.8.2)\n",
+      "Requirement already satisfied: pillow>=6.2.0 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from matplotlib>=2.0.0->pyannote.metrics<4.0,>=3.2->pyannote.audio->-r requirements.txt (line 2)) (9.2.0)\n",
+      "Collecting kiwisolver>=1.0.1\n",
+      "  Downloading kiwisolver-1.4.4-cp39-cp39-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (1.6 MB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.6/1.6 MB\u001b[0m \u001b[31m44.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m\n",
+      "\u001b[?25hRequirement already satisfied: pyparsing>=2.2.1 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from matplotlib>=2.0.0->pyannote.metrics<4.0,>=3.2->pyannote.audio->-r requirements.txt (line 2)) (3.0.9)\n",
+      "Collecting contourpy>=1.0.1\n",
+      "  Downloading contourpy-1.0.5-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (296 kB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m296.3/296.3 kB\u001b[0m \u001b[31m27.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+      "\u001b[?25hCollecting fonttools>=4.22.0\n",
+      "  Downloading fonttools-4.37.4-py3-none-any.whl (960 kB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m960.8/960.8 kB\u001b[0m \u001b[31m44.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+      "\u001b[?25hCollecting cmaes>=0.8.2\n",
+      "  Downloading cmaes-0.8.2-py3-none-any.whl (15 kB)\n",
+      "Collecting sqlalchemy>=1.3.0\n",
+      "  Downloading SQLAlchemy-1.4.41-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.6 MB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.6/1.6 MB\u001b[0m \u001b[31m93.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+      "\u001b[?25hCollecting alembic>=1.5.0\n",
+      "  Downloading alembic-1.8.1-py3-none-any.whl (209 kB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m209.8/209.8 kB\u001b[0m \u001b[31m19.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+      "\u001b[?25hRequirement already satisfied: colorlog in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from optuna>=1.4->pyannote.pipeline<3.0,>=2.3->pyannote.audio->-r requirements.txt (line 2)) (6.6.0)\n",
+      "Collecting cliff\n",
+      "  Downloading cliff-4.0.0-py3-none-any.whl (80 kB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m81.0/81.0 kB\u001b[0m \u001b[31m10.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+      "\u001b[?25hCollecting scipy>=0.19\n",
+      "  Downloading scipy-1.8.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (42.2 MB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m42.2/42.2 MB\u001b[0m \u001b[31m33.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
+      "\u001b[?25hRequirement already satisfied: pytz>=2020.1 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from pandas>=0.19->pyannote.database<5.0,>=4.1.1->pyannote.audio->-r requirements.txt (line 2)) (2022.2.1)\n",
+      "Requirement already satisfied: threadpoolctl>=2.0.0 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from scikit-learn>=0.16->hmmlearn<0.3,>=0.2.7->pyannote.audio->-r requirements.txt (line 2)) (3.1.0)\n",
+      "Requirement already satisfied: mpmath>=0.19 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from sympy>=1.1->pyannote.metrics<4.0,>=3.2->pyannote.audio->-r requirements.txt (line 2)) (1.2.1)\n",
+      "Requirement already satisfied: tensorboard-plugin-wit>=1.6.0 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from tensorboard>=2.2.0->pytorch-lightning<1.7,>=1.5.4->pyannote.audio->-r requirements.txt (line 2)) (1.8.1)\n",
+      "Requirement already satisfied: wheel>=0.26 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from tensorboard>=2.2.0->pytorch-lightning<1.7,>=1.5.4->pyannote.audio->-r requirements.txt (line 2)) (0.37.1)\n",
+      "Requirement already satisfied: werkzeug>=1.0.1 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from tensorboard>=2.2.0->pytorch-lightning<1.7,>=1.5.4->pyannote.audio->-r requirements.txt (line 2)) (2.2.2)\n",
+      "Requirement already satisfied: setuptools>=41.0.0 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from tensorboard>=2.2.0->pytorch-lightning<1.7,>=1.5.4->pyannote.audio->-r requirements.txt (line 2)) (65.0.0)\n",
+      "Requirement already satisfied: grpcio>=1.24.3 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from tensorboard>=2.2.0->pytorch-lightning<1.7,>=1.5.4->pyannote.audio->-r requirements.txt (line 2)) (1.47.0)\n",
+      "Requirement already satisfied: tensorboard-data-server<0.7.0,>=0.6.0 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from tensorboard>=2.2.0->pytorch-lightning<1.7,>=1.5.4->pyannote.audio->-r requirements.txt (line 2)) (0.6.1)\n",
+      "Requirement already satisfied: markdown>=2.6.8 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from tensorboard>=2.2.0->pytorch-lightning<1.7,>=1.5.4->pyannote.audio->-r requirements.txt (line 2)) (3.4.1)\n",
+      "Requirement already satisfied: google-auth<3,>=1.6.3 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from tensorboard>=2.2.0->pytorch-lightning<1.7,>=1.5.4->pyannote.audio->-r requirements.txt (line 2)) (2.11.0)\n",
+      "Requirement already satisfied: google-auth-oauthlib<0.5,>=0.4.1 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from tensorboard>=2.2.0->pytorch-lightning<1.7,>=1.5.4->pyannote.audio->-r requirements.txt (line 2)) (0.4.6)\n",
+      "Requirement already satisfied: absl-py>=0.4 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from tensorboard>=2.2.0->pytorch-lightning<1.7,>=1.5.4->pyannote.audio->-r requirements.txt (line 2)) (1.2.0)\n",
+      "Requirement already satisfied: certifi>=2017.4.17 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from requests->huggingface-hub<0.9,>=0.7->pyannote.audio->-r requirements.txt (line 2)) (2022.6.15)\n",
+      "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from requests->huggingface-hub<0.9,>=0.7->pyannote.audio->-r requirements.txt (line 2)) (1.26.11)\n",
+      "Requirement already satisfied: idna<4,>=2.5 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from requests->huggingface-hub<0.9,>=0.7->pyannote.audio->-r requirements.txt (line 2)) (3.3)\n",
+      "Requirement already satisfied: charset-normalizer<3,>=2 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from requests->huggingface-hub<0.9,>=0.7->pyannote.audio->-r requirements.txt (line 2)) (2.1.0)\n",
+      "Collecting primePy>=1.3\n",
+      "  Downloading primePy-1.3-py3-none-any.whl (4.0 kB)\n",
+      "Requirement already satisfied: click<9.0.0,>=7.1.1 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from typer[all]>=0.2.1->pyannote.database<5.0,>=4.1.1->pyannote.audio->-r requirements.txt (line 2)) (8.1.3)\n",
+      "Collecting rich<13.0.0,>=10.11.0\n",
+      "  Downloading rich-12.6.0-py3-none-any.whl (237 kB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m237.5/237.5 kB\u001b[0m \u001b[31m25.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+      "\u001b[?25hCollecting shellingham<2.0.0,>=1.3.0\n",
+      "  Downloading shellingham-1.5.0-py2.py3-none-any.whl (9.3 kB)\n",
+      "Requirement already satisfied: colorama<0.5.0,>=0.4.3 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from typer[all]>=0.2.1->pyannote.database<5.0,>=4.1.1->pyannote.audio->-r requirements.txt (line 2)) (0.4.5)\n",
+      "Collecting ruamel.yaml>=0.17.8\n",
+      "  Downloading ruamel.yaml-0.17.21-py3-none-any.whl (109 kB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m109.5/109.5 kB\u001b[0m \u001b[31m9.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+      "\u001b[?25hCollecting torchvision\n",
+      "  Using cached torchvision-0.13.1-cp39-cp39-manylinux1_x86_64.whl (19.1 MB)\n",
+      "Collecting Mako\n",
+      "  Downloading Mako-1.2.3-py3-none-any.whl (78 kB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m78.7/78.7 kB\u001b[0m \u001b[31m9.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+      "\u001b[?25hRequirement already satisfied: rsa<5,>=3.1.4 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from google-auth<3,>=1.6.3->tensorboard>=2.2.0->pytorch-lightning<1.7,>=1.5.4->pyannote.audio->-r requirements.txt (line 2)) (4.9)\n",
+      "Requirement already satisfied: pyasn1-modules>=0.2.1 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from google-auth<3,>=1.6.3->tensorboard>=2.2.0->pytorch-lightning<1.7,>=1.5.4->pyannote.audio->-r requirements.txt (line 2)) (0.2.8)\n",
+      "Requirement already satisfied: cachetools<6.0,>=2.0.0 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from google-auth<3,>=1.6.3->tensorboard>=2.2.0->pytorch-lightning<1.7,>=1.5.4->pyannote.audio->-r requirements.txt (line 2)) (5.2.0)\n",
+      "Requirement already satisfied: six>=1.9.0 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from google-auth<3,>=1.6.3->tensorboard>=2.2.0->pytorch-lightning<1.7,>=1.5.4->pyannote.audio->-r requirements.txt (line 2)) (1.16.0)\n",
+      "Requirement already satisfied: requests-oauthlib>=0.7.0 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from google-auth-oauthlib<0.5,>=0.4.1->tensorboard>=2.2.0->pytorch-lightning<1.7,>=1.5.4->pyannote.audio->-r requirements.txt (line 2)) (1.3.1)\n",
+      "Requirement already satisfied: importlib-metadata>=4.4 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from markdown>=2.6.8->tensorboard>=2.2.0->pytorch-lightning<1.7,>=1.5.4->pyannote.audio->-r requirements.txt (line 2)) (4.11.4)\n",
+      "Requirement already satisfied: llvmlite<0.40,>=0.39.0dev0 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from numba>=0.45.1->librosa>=0.6.0->torch-audiomentations>=0.11.0->pyannote.audio->-r requirements.txt (line 2)) (0.39.0)\n",
+      "Requirement already satisfied: appdirs>=1.3.0 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from pooch>=1.0->librosa>=0.6.0->torch-audiomentations>=0.11.0->pyannote.audio->-r requirements.txt (line 2)) (1.4.4)\n",
+      "Requirement already satisfied: pygments<3.0.0,>=2.6.0 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from rich<13.0.0,>=10.11.0->typer[all]>=0.2.1->pyannote.database<5.0,>=4.1.1->pyannote.audio->-r requirements.txt (line 2)) (2.12.0)\n",
+      "Collecting commonmark<0.10.0,>=0.9.0\n",
+      "  Downloading commonmark-0.9.1-py2.py3-none-any.whl (51 kB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m51.1/51.1 kB\u001b[0m \u001b[31m4.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+      "\u001b[?25hCollecting ruamel.yaml.clib>=0.2.6\n",
+      "  Downloading ruamel.yaml.clib-0.2.6-cp39-cp39-manylinux1_x86_64.whl (539 kB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m539.7/539.7 kB\u001b[0m \u001b[31m36.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+      "\u001b[?25hCollecting greenlet!=0.4.17\n",
+      "  Downloading greenlet-1.1.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (154 kB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m154.1/154.1 kB\u001b[0m \u001b[31m18.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+      "\u001b[?25hRequirement already satisfied: MarkupSafe>=2.1.1 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from werkzeug>=1.0.1->tensorboard>=2.2.0->pytorch-lightning<1.7,>=1.5.4->pyannote.audio->-r requirements.txt (line 2)) (2.1.1)\n",
+      "Requirement already satisfied: multidict<7.0,>=4.5 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from aiohttp->fsspec[http]!=2021.06.0,>=2021.05.0->pytorch-lightning<1.7,>=1.5.4->pyannote.audio->-r requirements.txt (line 2)) (6.0.2)\n",
+      "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from aiohttp->fsspec[http]!=2021.06.0,>=2021.05.0->pytorch-lightning<1.7,>=1.5.4->pyannote.audio->-r requirements.txt (line 2)) (4.0.2)\n",
+      "Requirement already satisfied: frozenlist>=1.1.1 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from aiohttp->fsspec[http]!=2021.06.0,>=2021.05.0->pytorch-lightning<1.7,>=1.5.4->pyannote.audio->-r requirements.txt (line 2)) (1.3.1)\n",
+      "Requirement already satisfied: attrs>=17.3.0 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from aiohttp->fsspec[http]!=2021.06.0,>=2021.05.0->pytorch-lightning<1.7,>=1.5.4->pyannote.audio->-r requirements.txt (line 2)) (22.1.0)\n",
+      "Requirement already satisfied: yarl<2.0,>=1.0 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from aiohttp->fsspec[http]!=2021.06.0,>=2021.05.0->pytorch-lightning<1.7,>=1.5.4->pyannote.audio->-r requirements.txt (line 2)) (1.8.1)\n",
+      "Requirement already satisfied: aiosignal>=1.1.2 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from aiohttp->fsspec[http]!=2021.06.0,>=2021.05.0->pytorch-lightning<1.7,>=1.5.4->pyannote.audio->-r requirements.txt (line 2)) (1.2.0)\n",
+      "Collecting autopage>=0.4.0\n",
+      "  Downloading autopage-0.5.1-py3-none-any.whl (29 kB)\n",
+      "Collecting cmd2>=1.0.0\n",
+      "  Downloading cmd2-2.4.2-py3-none-any.whl (147 kB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m147.1/147.1 kB\u001b[0m \u001b[31m7.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+      "\u001b[?25hCollecting stevedore>=2.0.1\n",
+      "  Downloading stevedore-4.0.0-py3-none-any.whl (49 kB)\n",
+      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m49.5/49.5 kB\u001b[0m \u001b[31m5.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+      "\u001b[?25hCollecting PrettyTable>=0.7.2\n",
+      "  Downloading prettytable-3.4.1-py3-none-any.whl (26 kB)\n",
+      "Requirement already satisfied: wcwidth>=0.1.7 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from cmd2>=1.0.0->cliff->optuna>=1.4->pyannote.pipeline<3.0,>=2.3->pyannote.audio->-r requirements.txt (line 2)) (0.2.5)\n",
+      "Collecting pyperclip>=1.6\n",
+      "  Downloading pyperclip-1.8.2.tar.gz (20 kB)\n",
+      "  Preparing metadata (setup.py) ... \u001b[?25ldone\n",
+      "\u001b[?25hRequirement already satisfied: zipp>=0.5 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from importlib-metadata>=4.4->markdown>=2.6.8->tensorboard>=2.2.0->pytorch-lightning<1.7,>=1.5.4->pyannote.audio->-r requirements.txt (line 2)) (3.8.1)\n",
+      "Requirement already satisfied: pyasn1<0.5.0,>=0.4.6 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from pyasn1-modules>=0.2.1->google-auth<3,>=1.6.3->tensorboard>=2.2.0->pytorch-lightning<1.7,>=1.5.4->pyannote.audio->-r requirements.txt (line 2)) (0.4.8)\n",
+      "Requirement already satisfied: oauthlib>=3.0.0 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<0.5,>=0.4.1->tensorboard>=2.2.0->pytorch-lightning<1.7,>=1.5.4->pyannote.audio->-r requirements.txt (line 2)) (3.2.0)\n",
+      "Requirement already satisfied: pbr!=2.1.0,>=2.0.0 in /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages (from stevedore>=2.0.1->cliff->optuna>=1.4->pyannote.pipeline<3.0,>=2.3->pyannote.audio->-r requirements.txt (line 2)) (5.10.0)\n",
+      "Building wheels for collected packages: antlr4-python3-runtime, docopt, julius, hyperpyyaml, pyperclip\n",
+      "  Building wheel for antlr4-python3-runtime (setup.py) ... \u001b[?25ldone\n",
+      "\u001b[?25h  Created wheel for antlr4-python3-runtime: filename=antlr4_python3_runtime-4.9.3-py3-none-any.whl size=144554 sha256=66a81504d29d763868c1dfe04d45cca872f78e97b7b92112e556731e2cab617d\n",
+      "  Stored in directory: /home/ubuntu/.cache/pip/wheels/23/cf/80/f3efa822e6ab23277902ee9165fe772eeb1dfb8014f359020a\n",
+      "  Building wheel for docopt (setup.py) ... \u001b[?25ldone\n",
+      "\u001b[?25h  Created wheel for docopt: filename=docopt-0.6.2-py2.py3-none-any.whl size=13706 sha256=3805c1a127c79f3a81ed6be5ddee9d3313fd0aa7107216896e89e5cecf2bbe27\n",
+      "  Stored in directory: /home/ubuntu/.cache/pip/wheels/70/4a/46/1309fc853b8d395e60bafaf1b6df7845bdd82c95fd59dd8d2b\n",
+      "  Building wheel for julius (setup.py) ... \u001b[?25ldone\n",
+      "\u001b[?25h  Created wheel for julius: filename=julius-0.2.7-py3-none-any.whl size=21878 sha256=bf68d9142aaa911aa76fec8e020953044482054bd72a37b2f7c4a18e77edb1b0\n",
+      "  Stored in directory: /home/ubuntu/.cache/pip/wheels/53/0a/a7/fc08f97438f4969d86afa7904336c2eb7eb422101359f3ad11\n",
+      "  Building wheel for hyperpyyaml (setup.py) ... \u001b[?25ldone\n",
+      "\u001b[?25h  Created wheel for hyperpyyaml: filename=HyperPyYAML-1.0.1-py3-none-any.whl size=15174 sha256=4c1e243d17ff4f7740e60bbe69d33602ef80a0011868ac15fc5b1dbc63ad5c70\n",
+      "  Stored in directory: /home/ubuntu/.cache/pip/wheels/c2/bb/de/befc66499e9c2b4b8b163e018abcace61c80220e6a28950a65\n",
+      "  Building wheel for pyperclip (setup.py) ... \u001b[?25ldone\n",
+      "\u001b[?25h  Created wheel for pyperclip: filename=pyperclip-1.8.2-py3-none-any.whl size=11123 sha256=a6734b9b91c358d2e5d4e4c3c8e8d0a02f2aab94ecca213c41935d81630367e8\n",
+      "  Stored in directory: /home/ubuntu/.cache/pip/wheels/0c/09/9e/49e21a6840ef7955b06d47394afef0058f0378c0914e48b8b8\n",
+      "Successfully built antlr4-python3-runtime docopt julius hyperpyyaml pyperclip\n",
+      "Installing collected packages: singledispatchmethod, pyperclip, primePy, einops, docopt, commonmark, antlr4-python3-runtime, typer, torch, stevedore, simplejson, shellingham, semver, scipy, ruamel.yaml.clib, rich, pyDeprecate, PrettyTable, omegaconf, networkx, Mako, kiwisolver, greenlet, fonttools, cycler, contourpy, cmd2, cmaes, backports.cached-property, autopage, torchvision, torchmetrics, torchaudio, sqlalchemy, ruamel.yaml, pyannote.core, matplotlib, julius, huggingface-hub, cliff, asteroid-filterbanks, torch-pitch-shift, pytorch-metric-learning, pyannote.database, hyperpyyaml, hmmlearn, alembic, torch-audiomentations, speechbrain, pyannote.metrics, optuna, pytorch-lightning, pyannote.pipeline, pyannote.audio\n",
+      "  Attempting uninstall: torch\n",
+      "    Found existing installation: torch 1.11.0+cu113\n",
+      "    Uninstalling torch-1.11.0+cu113:\n",
+      "      Successfully uninstalled torch-1.11.0+cu113\n",
+      "  Attempting uninstall: scipy\n",
+      "    Found existing installation: scipy 1.9.0\n",
+      "    Uninstalling scipy-1.9.0:\n",
+      "      Successfully uninstalled scipy-1.9.0\n",
+      "  Attempting uninstall: torchvision\n",
+      "    Found existing installation: torchvision 0.12.0+cu113\n",
+      "    Uninstalling torchvision-0.12.0+cu113:\n",
+      "      Successfully uninstalled torchvision-0.12.0+cu113\n",
+      "  Attempting uninstall: huggingface-hub\n",
+      "    Found existing installation: huggingface-hub 0.9.0\n",
+      "    Uninstalling huggingface-hub-0.9.0:\n",
+      "      Successfully uninstalled huggingface-hub-0.9.0\n",
+      "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
+      "huggingface-inference-toolkit 0.1.0 requires torchvision<=0.12.0, but you have torchvision 0.13.1 which is incompatible.\u001b[0m\u001b[31m\n",
+      "\u001b[0mSuccessfully installed Mako-1.2.3 PrettyTable-3.4.1 alembic-1.8.1 antlr4-python3-runtime-4.9.3 asteroid-filterbanks-0.4.0 autopage-0.5.1 backports.cached-property-1.0.2 cliff-4.0.0 cmaes-0.8.2 cmd2-2.4.2 commonmark-0.9.1 contourpy-1.0.5 cycler-0.11.0 docopt-0.6.2 einops-0.3.2 fonttools-4.37.4 greenlet-1.1.3 hmmlearn-0.2.8 huggingface-hub-0.8.1 hyperpyyaml-1.0.1 julius-0.2.7 kiwisolver-1.4.4 matplotlib-3.6.0 networkx-2.8.7 omegaconf-2.2.3 optuna-3.0.2 primePy-1.3 pyDeprecate-0.3.2 pyannote.audio-2.0.1 pyannote.core-4.5 pyannote.database-4.1.3 pyannote.metrics-3.2.1 pyannote.pipeline-2.3 pyperclip-1.8.2 pytorch-lightning-1.6.5 pytorch-metric-learning-1.6.2 rich-12.6.0 ruamel.yaml-0.17.21 ruamel.yaml.clib-0.2.6 scipy-1.8.1 semver-2.13.0 shellingham-1.5.0 simplejson-3.17.6 singledispatchmethod-1.0 speechbrain-0.5.13 sqlalchemy-1.4.41 stevedore-4.0.0 torch-1.12.1 torch-audiomentations-0.11.0 torch-pitch-shift-1.2.2 torchaudio-0.12.1 torchmetrics-0.10.0 torchvision-0.13.1 typer-0.6.1\n"
+     ]
+    }
+   ],
+   "source": [
+    "!pip install -r requirements.txt --upgrade"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "9caf5b409e794ecea978b87f399cf3f1",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading:   0%|          | 0.00/598 [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "0072f6911e7d402ea0fd0437c7841ddb",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading:   0%|          | 0.00/17.7M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "2fff59eb41574f1aa5e159ced85b98a4",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading:   0%|          | 0.00/318 [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "a880484a957642faa87db557521f3cee",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading:   0%|          | 0.00/1.92k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "c655e7a82a354464aa0a82dee1eaf35f",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading:   0%|          | 0.00/83.3M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "b3b18c63fb344e9986502276819a1aab",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading:   0%|          | 0.00/1.92k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "92af59a51c314e6cb1915cadd2ab9a03",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading:   0%|          | 0.00/5.53M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "63adf3749baa487096fc6f281f635d85",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading:   0%|          | 0.00/129k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "start=0.5s stop=1.4s speaker_SPEAKER_01\n",
+      "start=1.9s stop=2.8s speaker_SPEAKER_01\n",
+      "start=3.0s stop=3.5s speaker_SPEAKER_02\n",
+      "start=3.6s stop=4.3s speaker_SPEAKER_01\n",
+      "start=4.6s stop=6.8s speaker_SPEAKER_02\n",
+      "start=7.1s stop=7.6s speaker_SPEAKER_00\n",
+      "start=7.6s stop=9.5s speaker_SPEAKER_02\n",
+      "start=9.8s stop=10.6s speaker_SPEAKER_02\n",
+      "start=9.9s stop=10.4s speaker_SPEAKER_00\n",
+      "start=12.4s stop=15.6s speaker_SPEAKER_03\n",
+      "start=15.8s stop=16.1s speaker_SPEAKER_00\n",
+      "start=16.1s stop=16.2s speaker_SPEAKER_01\n",
+      "start=17.2s stop=17.4s speaker_SPEAKER_00\n",
+      "start=17.7s stop=20.4s speaker_SPEAKER_01\n",
+      "start=20.6s stop=20.7s speaker_SPEAKER_01\n",
+      "start=20.7s stop=20.8s speaker_SPEAKER_00\n",
+      "start=20.8s stop=20.9s speaker_SPEAKER_01\n",
+      "start=21.1s stop=22.1s speaker_SPEAKER_01\n",
+      "start=22.5s stop=22.7s speaker_SPEAKER_02\n",
+      "start=23.2s stop=23.5s speaker_SPEAKER_02\n",
+      "start=23.5s stop=24.0s speaker_SPEAKER_01\n",
+      "start=24.3s stop=25.5s speaker_SPEAKER_02\n",
+      "start=25.8s stop=27.3s speaker_SPEAKER_01\n",
+      "start=27.3s stop=27.5s speaker_SPEAKER_02\n",
+      "start=29.7s stop=30.0s speaker_SPEAKER_01\n"
+     ]
+    }
+   ],
+   "source": [
+    "from pyannote.audio import Pipeline\n",
+    "pipeline = Pipeline.from_pretrained(\"pyannote/speaker-diarization\")\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from transformers.pipelines.audio_utils import ffmpeg_read\n",
+    "import torch\n",
+    "\n",
+    "\n",
+    "\n",
+    "\n",
+    "audio_nparray = ffmpeg_read(request[\"inputs\"], 16000)\n",
+    "audio_tensor= torch.from_numpy(audio_nparray).unsqueeze(0)\n",
+    "f = {\"waveform\": audio_tensor, \"sample_rate\": 16000}"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 2. Create Custom Handler for Inference Endpoints\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Overwriting handler.py\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%writefile handler.py\n",
+    "from typing import  Dict\n",
+    "from pyannote.audio import Pipeline\n",
+    "from transformers.pipelines.audio_utils import ffmpeg_read\n",
+    "import torch \n",
+    "\n",
+    "SAMPLE_RATE = 16000\n",
+    "\n",
+    "\n",
+    "\n",
+    "class EndpointHandler():\n",
+    "    def __init__(self, path=\"\"):\n",
+    "        # load the model\n",
+    "        self.pipeline = Pipeline.from_pretrained(\"pyannote/speaker-diarization\")\n",
+    "\n",
+    "\n",
+    "    def __call__(self, data: Dict[str, bytes]) -> Dict[str, str]:\n",
+    "        \"\"\"\n",
+    "        Args:\n",
+    "            data (:obj:):\n",
+    "                includes the deserialized audio file as bytes\n",
+    "        Return:\n",
+    "            A :obj:`dict`:. base64 encoded image\n",
+    "        \"\"\"\n",
+    "        # process input\n",
+    "        inputs = data.pop(\"inputs\", data)\n",
+    "        parameters = data.pop(\"parameters\", None) #  min_speakers=2, max_speakers=5\n",
+    "\n",
+    "        \n",
+    "        # prepare pynannote input\n",
+    "        audio_nparray = ffmpeg_read(inputs, SAMPLE_RATE)\n",
+    "        audio_tensor= torch.from_numpy(audio_nparray).unsqueeze(0)\n",
+    "        pyannote_input = {\"waveform\": audio_tensor, \"sample_rate\": SAMPLE_RATE}\n",
+    "        \n",
+    "        # apply pretrained pipeline\n",
+    "        # pass inputs with all kwargs in data\n",
+    "        if parameters is not None:\n",
+    "            diarization = self.pipeline(pyannote_input, **parameters)\n",
+    "        else:\n",
+    "            diarization = self.pipeline(pyannote_input)\n",
+    "\n",
+    "        # postprocess the prediction\n",
+    "        processed_diarization = [\n",
+    "            {\"label\": str(label), \"start\": str(segment.start), \"stop\": str(segment.end)}\n",
+    "            for segment, _, label in diarization.itertracks(yield_label=True)\n",
+    "        ]\n",
+    "        \n",
+    "        return {\"diarization\": processed_diarization}"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "test custom pipeline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from handler import EndpointHandler\n",
+    "\n",
+    "# init handler\n",
+    "my_handler = EndpointHandler(path=\".\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import base64\n",
+    "from PIL import Image\n",
+    "from io import BytesIO\n",
+    "import json\n",
+    "\n",
+    "# file reader\n",
+    "with open(\"sample.wav\", \"rb\") as f:\n",
+    "  request = {\"inputs\": f.read()}\n",
+    "\n",
+    "# test the handler\n",
+    "pred = my_handler(request)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'diarization': [{'label': 'SPEAKER_01',\n",
+       "   'start': '0.4978125',\n",
+       "   'stop': '1.3921875'},\n",
+       "  {'label': 'SPEAKER_01', 'start': '1.8984375', 'stop': '2.7590624999999998'},\n",
+       "  {'label': 'SPEAKER_02', 'start': '2.9953125', 'stop': '3.5015625000000004'},\n",
+       "  {'label': 'SPEAKER_01',\n",
+       "   'start': '3.5690625000000002',\n",
+       "   'stop': '4.311562500000001'},\n",
+       "  {'label': 'SPEAKER_02', 'start': '4.6153125', 'stop': '6.7753125'},\n",
+       "  {'label': 'SPEAKER_00', 'start': '7.1128125', 'stop': '7.551562500000001'},\n",
+       "  {'label': 'SPEAKER_02',\n",
+       "   'start': '7.551562500000001',\n",
+       "   'stop': '9.475312500000001'},\n",
+       "  {'label': 'SPEAKER_02',\n",
+       "   'start': '9.812812500000003',\n",
+       "   'stop': '10.555312500000003'},\n",
+       "  {'label': 'SPEAKER_00',\n",
+       "   'start': '9.863437500000003',\n",
+       "   'stop': '10.420312500000001'},\n",
+       "  {'label': 'SPEAKER_03', 'start': '12.411562500000002', 'stop': '15.5503125'},\n",
+       "  {'label': 'SPEAKER_00', 'start': '15.786562500000002', 'stop': '16.1409375'},\n",
+       "  {'label': 'SPEAKER_01', 'start': '16.1409375', 'stop': '16.1578125'},\n",
+       "  {'label': 'SPEAKER_00', 'start': '17.1534375', 'stop': '17.4234375'},\n",
+       "  {'label': 'SPEAKER_01', 'start': '17.7440625', 'stop': '20.3596875'},\n",
+       "  {'label': 'SPEAKER_01', 'start': '20.6128125', 'stop': '20.6634375'},\n",
+       "  {'label': 'SPEAKER_00', 'start': '20.6634375', 'stop': '20.8490625'},\n",
+       "  {'label': 'SPEAKER_01', 'start': '20.8490625', 'stop': '20.8828125'},\n",
+       "  {'label': 'SPEAKER_01', 'start': '21.1021875', 'stop': '22.1315625'},\n",
+       "  {'label': 'SPEAKER_02', 'start': '22.4521875', 'stop': '22.7053125'},\n",
+       "  {'label': 'SPEAKER_02', 'start': '23.2115625', 'stop': '23.4815625'},\n",
+       "  {'label': 'SPEAKER_01', 'start': '23.4815625', 'stop': '24.0215625'},\n",
+       "  {'label': 'SPEAKER_02', 'start': '24.3253125', 'stop': '25.5065625'},\n",
+       "  {'label': 'SPEAKER_01', 'start': '25.8440625', 'stop': '27.3121875'},\n",
+       "  {'label': 'SPEAKER_02', 'start': '27.3121875', 'stop': '27.4978125'},\n",
+       "  {'label': 'SPEAKER_01', 'start': '29.7253125', 'stop': '29.9615625'}]}"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "pred"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.9.13 ('dev': conda)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.13"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "f6dd96c16031089903d5a31ec148b80aeb0d39c32affb1a1080393235fbfa2fc"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

handler.py ADDED Viewed

	@@ -0,0 +1,47 @@

+from typing import  Dict
+from pyannote.audio import Pipeline
+from transformers.pipelines.audio_utils import ffmpeg_read
+import torch
+SAMPLE_RATE = 16000
+class EndpointHandler():
+    def __init__(self, path=""):
+        # load the model
+        self.pipeline = Pipeline.from_pretrained("pyannote/speaker-diarization")
+    def __call__(self, data: Dict[str, bytes]) -> Dict[str, str]:
+        """
+        Args:
+            data (:obj:):
+                includes the deserialized audio file as bytes
+        Return:
+            A :obj:`dict`:. base64 encoded image
+        """
+        # process input
+        inputs = data.pop("inputs", data)
+        parameters = data.pop("parameters", None) #  min_speakers=2, max_speakers=5
+        # prepare pynannote input
+        audio_nparray = ffmpeg_read(inputs, SAMPLE_RATE)
+        audio_tensor= torch.from_numpy(audio_nparray).unsqueeze(0)
+        pyannote_input = {"waveform": audio_tensor, "sample_rate": SAMPLE_RATE}
+        # apply pretrained pipeline
+        # pass inputs with all kwargs in data
+        if parameters is not None:
+            diarization = self.pipeline(pyannote_input, **parameters)
+        else:
+            diarization = self.pipeline(pyannote_input)
+        # postprocess the prediction
+        processed_diarization = [
+            {"label": str(label), "start": str(segment.start), "stop": str(segment.end)}
+            for segment, _, label in diarization.itertracks(yield_label=True)
+        ]
+        return {"diarization": processed_diarization}

requirements.txt ADDED Viewed

	@@ -0,0 +1,2 @@


1	+ torchaudio
2	+ pyannote.audio