doc: describe offline use (#1169)

* related bugs: #1119 #1128 #1130
* related discussions: #1123 #1103 #1126 #1121
This commit is contained in:
Hervé BREDIN authored and GitHub committed 2022-11-29 18:14:49 +01:00
1 parent 789b8d4766
commit a1e99ee550
6 files changed
+284 -107

No files matched your search

+25
View File
@@ -0,0 +1,25 @@
# Frequently asked questions
## How does one capitalize and pronounce the name of this awesome library?
📝 Written in lower case: `pyannote.audio` (or `pyannote` if you are lazy). Not `PyAnnote` nor `PyAnnotate` (*sic*).
📢 [Pronounced](https://www.howtopronounce.com/french/pianote) like the french verb *pianoter*. *pi* like in **pi**ano, not *py* like in **py**thon.
🎹 *pianoter* means *to play the piano* (hence the logo 🤯).
## Can I use gated models (and pipelines) offline?
**Short answer**: yes, see [this tutorial](tutorials/applying_a_model.ipynb) for models and [that one](tutorials/applying_a_pipeline.ipynb) for pipelines.
**Long answer**: gating models and pipelines allows [me](https://herve.niderb.fr) to know a bit more about `pyannote.audio` user base and eventually help me write grant proposals to make `pyannote.audio` even better. So, please fill gating forms as precisely as possible.
For instance, before gating `pyannote/speaker-diarization`, I had no idea that so many people were relying on it in production. Hint: sponsors are more than welcome! Maintaining open source libraries is time consuming.
That being said, this whole authentication process does not prevent you from using official `pyannote.audio` models offline (i.e. without going through the authentication process in every `docker run ...` or whatever you are using in production): see [this tutorial](tutorials/applying_a_model.ipynb) for models and [that one](tutorials/applying_a_pipeline.ipynb) for pipelines.
## **[Pretrained pipelines](https://huggingface.co/models?other=pyannote-audio-pipeline) do not produce good results on my data. What can I do?**
1. [Annotate](https://github.com/pyannote/pyannote-audio/blob/develop/tutorials/prodigy.md) dozens of conversations manually and separate them into development and test subsets in [`pyannote.database`](https://github.com/pyannote/pyannote-database#speaker-diarization).
2. [Optimize the hyper-parameters](https://github.com/pyannote/pyannote-audio/blob/develop/tutorials/voice_activity_detection.ipynb) of the pretained pipeline using the development set. If performance is still not good enough, go to step 3.
3. Annotate hundreds of conversations manually and set them up as training subset in `pyannote.database`.
4. [Fine-tune](https://github.com/pyannote/pyannote-audio/blob/develop/tutorials/training_a_model.ipynb) the models (on which the pipeline relies) using the training set.
5. [Optimize the hyper-parameters](https://github.com/pyannote/pyannote-audio/blob/develop/tutorials/voice_activity_detection.ipynb) of the pipeline using the fine-tuned models using the development set. If performance is still not good enough, go back to step 3.
+3 -14
View File
@@ -84,20 +84,9 @@ pip install pyannote.audio
## Frequently asked questions
#### How does one capitalize and pronounce the name of this awesome library?
📝 Written in lower case: `pyannote.audio` (or `pyannote` if you are lazy). Not `PyAnnote` nor `PyAnnotate` (*sic*).
📢 [Pronounced](https://www.howtopronounce.com/french/pianote) like the french verb *pianoter*. *pi* like in **pi**ano, not *py* like in **py**thon.
🎹 *pianoter* means *to play the piano* (hence the logo 🤯).
#### **[Pretrained pipelines](https://huggingface.co/models?other=pyannote-audio-pipeline) do not produce good results on my data. What can I do?**
1. [Annotate](https://github.com/pyannote/pyannote-audio/blob/develop/tutorials/prodigy.md) dozens of conversations manually and separate them into development and test subsets in [`pyannote.database`](https://github.com/pyannote/pyannote-database#speaker-diarization).
2. [Optimize the hyper-parameters](https://github.com/pyannote/pyannote-audio/blob/develop/tutorials/voice_activity_detection.ipynb) of the pretained pipeline using the development set. If performance is still not good enough, go to step 3.
3. Annotate hundreds of conversations manually and set them up as training subset in `pyannote.database`.
4. [Fine-tune](https://github.com/pyannote/pyannote-audio/blob/develop/tutorials/training_a_model.ipynb) the models (on which the pipeline relies) using the training set.
5. [Optimize the hyper-parameters](https://github.com/pyannote/pyannote-audio/blob/develop/tutorials/voice_activity_detection.ipynb) of the pipeline using the fine-tuned models using the development set. If performance is still not good enough, go back to step 3.
* [How does one capitalize and pronounce the name of this awesome library?](FAQ.md)
* [Can I use gated models (and pipelines) offline?](FAQ.md)
* [Pretrained pipelines do not produce good results on my data. What can I do?](FAQ.md)
## Benchmark
+115 -48
View File
@@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "code",
"execution_count": null,
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
@@ -23,7 +23,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
@@ -34,17 +34,17 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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 truncated
"image/png": "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 truncated
"text/plain": [
"<pyannote.core.annotation.Annotation>"
"<pyannote.core.annotation.Annotation at 0x16a3c0370>"
]
},
"execution_count": null,
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
@@ -62,24 +62,25 @@
"source": [
"## Loading models from 🤗 hub\n",
"\n",
"Pretrained models are available on [🤗 Huggingface model hub](https://hf.co/models?other=pyannote-audio-model) and can be listed by looking for the [`pyannote-audio-model`](https://hf.co/models?other=pyannote-audio-model) tag."
"A bunch of pretrained models are available on [🤗 Huggingface model hub](https://hf.co/models?other=pyannote-audio-model) and can be listed by looking for the [`pyannote-audio-model`](https://hf.co/models?other=pyannote-audio-model) tag."
]
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 16,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['pyannote/segmentation',\n",
" 'pyannote/embedding',\n",
"['pyannote/Segmentation-PyanNet-DIHARD',\n",
" 'pyannote/TestModelForContinuousIntegration',\n",
" 'pyannote/Segmentation-PyanNet-DIHARD']"
" 'pyannote/embedding',\n",
" 'pyannote/segmentation',\n",
" 'pyannote/brouhaha']"
]
},
"execution_count": null,
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
@@ -87,35 +88,36 @@
"source": [
"from huggingface_hub import HfApi\n",
"available_models = [m.modelId for m in HfApi().list_models(filter=\"pyannote-audio-model\")]\n",
"available_models"
"list(filter(lambda p: p.startswith(\"pyannote/\"), available_models))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"To load the speaker segmentation model, \n",
"Official [pyannote.audio](https://github.com/pyannote/pyannote-audio) models (i.e. those under the [`pyannote` organization](https://hf.co/pyannote) umbrella) are open-source, but gated. It means that you have to first accept users conditions on their respective Huggingface page to access the pretrained weights and hyper-parameters. Despite this initial process, those models can perfectly be downloaded for later offline use: keep reading this tutorial until the end to learn how to do that.\n",
"\n",
"* accept the user conditions on [hf.co/pyannote/segmentation](https://hf.co/pyannote/segmentation).\n",
"* login using `notebook_login` below"
"For instance, to load the speaker segmentation model used in this tutorial, you have to visit [hf.co/pyannote/segmentation](https://hf.co/pyannote/segmentation), accept the terms, and log in using `notebook_login` below:"
]
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Login successful\n",
"Your token has been saved to /Users/hbredin/.huggingface/token\n",
"\u001b[1m\u001b[31mAuthenticated through git-credential store but this isn't the helper defined on your machine.\n",
"You might have to re-authenticate when pushing to the Hugging Face Hub. Run the following command in your terminal in case you want to set this credential helper as the default\n",
"\n",
"git config --global credential.helper store\u001b[0m\n"
]
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "1b7ac613e9e841c8903dc4932e183006",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
@@ -123,9 +125,16 @@
"notebook_login()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Once authenticated, you can load the model..."
]
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
@@ -142,7 +151,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 7,
"metadata": {},
"outputs": [
{
@@ -162,7 +171,7 @@
"5.891 Total estimated model params size (MB)"
]
},
"execution_count": null,
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
@@ -180,7 +189,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 8,
"metadata": {},
"outputs": [
{
@@ -189,7 +198,7 @@
"Specifications(problem=<Problem.MULTI_LABEL_CLASSIFICATION: 2>, resolution=<Resolution.FRAME: 1>, duration=5.0, warm_up=(0.0, 0.0), classes=['speaker#1', 'speaker#2', 'speaker#3'], permutation_invariant=True)"
]
},
"execution_count": null,
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
@@ -219,17 +228,17 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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 truncated
"image/png": "iVBORw0KGgoAAAANSUhEUgAABi4AAAGZCAYAAAAetMkNAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjYuMCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy89olMNAAAACXBIWXMAAA9hAAAPYQGoP6dpAADTZ0lEQVR4nOzdd2AcZ53/8ffMNvVuybbk3lsc2+m9EtIJgUCAEHo7erkf9TjuDg6OO2roJUDoSSgJ6QnpzUkc995lVavXrTO/P55dFVu2VXa1K/nzgs3Mzs7OPJLWszPzfb7P13Jd10VERERERERERERERCQD2OlugIiIiIiIiIiIiIiISIICFyIiIiIiIiIiIiIikjEUuBARERERERERERERkYyhwIWIiIiIiIiIiIiIiGQMBS5ERERERERERERERCRjKHAhIiIiIiIiIiIiIiIZQ4ELERERERERERERERHJGN7RvtFxHGpra8nPz8eyrGS2SUREREREREREREREJhjXdens7GT69OnY9ujzJkYduKitrWXGjBmj3rGIiIiIiIiIiIiIiEw+1dXVVFVVjfr9ow5c5Ofn9zWgoKBg1A0QEREREREREREREZGJr6OjgxkzZvTFD0Zr1IGLxPBQBQUFClyIiIiIiIiIiIiIiAjAmMtLqDi3iIiIiIiIiIiIiIhkDAUuREREREREREREREQkYyhwISIiIiIiIiIiIiIiGUOBCxERERERERERERERyRgKXIiIiIiIiIiIiIiISMZQ4EJERERERERERERERDKGAhciIiIiIiIiIiIiIpIxFLgQEREREREREREREZGMocCFiIiIiIiIiIiIiIhkDAUuREREREREREREREQkY3jT3QAREZHxFozECEUdYo5L1IlPY278udu3nmX1v8fqW2YNsWzgetZRy47c3mi2YR0xYzFgG9YR6wzYx+BlR7w3PrEtyPZ58HpOrv4MruviuBBzXLy2hW0P8UcTkZFzXXCi4MTAdcwDt3/edeMP5zivD5jniHUHvo7bvz2z8/73JNqCO0QjE474d3/Uwfs4B/NjbmOM+xjqC2TM28iUfRz5lgHreLMgf9rw3ncCkZhDTzhGbzhGOOoQcRwiMYdI1MVxXWzLwrLMrmzLij+ILxvwHLOebZtvzv71rAHvja9nc/T7jlwvCT+bSCZr6grhOOb8ysU1h2fMOZc74LB81GskDuNm+aD3D5gf+P6RsoY6nh9r3RT+Ux3JtlPV5lS1YaAj/0buyP9kx952krY1ms/RkNtJ4s+WTJYFXtvGE/9+8to2tk3f1GNZZPk85AZ0a1gylz6dIiKSeuFuiIUhFgUnYpbZXvPw5YA3kNorBOCZXU18+9Gd7GropCMYTem+Jiqfx5y8Zvs8ZPs9lOcHqCrO4fTZJbx+dSVZPo9ZMRaBnQ9BVz2EeyDSA6FOCHUAVv/f1ImadWMhM42G4p+D+CMan7oxsGywPPGpHb97FJ+3PeY12wtev7m55fEd/QPkVUDRTLOfcBeEugZPYxEc28ef2hfzbwdOIRIb/Ha/1ybgtYcMAJn5+PRYrw9aPnDLR2/DHnCzLHFTy2MffSMsEnMIRR1C0RjBiDPohltiPfPcGrDN+I03++h9HHf9YbQp8V6/16KqOIfrVk5neWXhCT5ZMunVb4ZfXB4PVkTjAQWRUSiaBW/5E5QvGdbqwUiMP79czVM7mzjQ3M3hrhA98WBFpjrymOqxBzwGPLctC6/HLLNtywTY48v8HrvvO8vvtYk5EIrG4t8XDqGI+R0kvj+ijumckbihHHPNfKI9Fhbx//cHXIgHaGDAa+Y7we+xyQt4ycvysrAin5tOm8EZc0rS90uVjPHa7zxNU1co3c0QkRHI9XuoKMxiaoF5VBRmUZEfYGphFhUFWUwtzGJKXuCk6+QmmcFy3dHFBjs6OigsLKS9vZ2CgoJkt0tERCa6ug3w0BegYTP0th5/XdsL/lzw50MgD/x5/dPEfE4ZlMyBkrnmkVM6+O6w68LhHXBorZlWLIMVbwSPj4PNPVz6rSeIxIb+yvN5zE0Cr20P6hGZ+Ioc9C6Xo5YNtV5fr7ABS90h3stx1hu47sCva3eI9VJtZkkO3795FSsr/PD7m2D/0+O38xT4VPgD3O1ckO5mTHge2+L37zmTM+eWprspkk4NW+BH54zyzdbRwUrLHrDcjt8xPXK5dfTzxN3Vvu1aA6bxZYMccRA96qA6xEH2ROsc9ZYR7mPIA/tYt5GOfZxg+0NtI9xppsVz4EMvgC9riHb2i8Qc3vWrl3h6V9Mx1/HYFgGvjde28Hvtvu95F3DiWXemR7c74Hmix3d/r/Ghlstgn7tyMe+/cF66myFpdubXHuVwZ6gv6DVUYGxQRhIcFRgbGDSz4iv0ZUQxeJ3hGO4tr+H+sx7u+fdwe/MPf3vDXG/Yx6fkti+xxWN35IGjv4dHZiz93May57H2rxtt1spY9t3/fWVGFIjFXGLxeeeIUQaG244peQHml+exorKQ162qZMk03QuWY0tW3ECBCxERSb7DO+Bnl5he7key48l+zhizHvz5kFsK2cXgy4XmXdDVMHid5W+AG3/Or57bz7/fu5WZJTn89O1rmF6UTZbXMymHBxoU4BhmkCXmuIQiDr2RGL2RGD3hKD3hGA0dQXY3dvHHtdXUdwTxeSzuPuUlTtn2LRNQmnuRCTj5csw0q8hsMNID0aD5W3v8JvvC4wNPfOoNmOWJh+05YhiYAcPBODGTkeHE+jM4okGTxTHwIsB1oKMG2mvMzS5/Pk0RH+vqo2xpitEaCxDBy5X2Wi7wbKI3eyrd734GT3Yhtm0yGxJDiB35+xv4WxwqqHT08mMEoQYEqRJDHzhH3CxzBixz3f4skIDXQ8Br47GtvvXNOgPe49D3viO3G3OOvY9jbs8l3jv36NdDkRj3bKhl3cE2qoqzeeBj55OfNUQWjJwcomHorO3PpLO9/ZlSA4MRRwUoJtfxV8aoswF+fC50H4a33wNzLzzu6j9/ei//dd82snw2H7lkASsqC5lWmEVOwEuu30OO34vfm7reoUMFOAY9P1YgJD4sTiyRBRE/Rsccc1PJZEZA1HHir3HE686AbArz8MYDNInvioCvf97vtfF5rL6MOk/83Cdx+jPSoXxc1yUUdegORWnrjfDQlnr+sq4GgB++dTVXrZiWst+5iIgkj+O49ETMNV9De5CGziD17SEaOoLUx583tAdp7AwdFeiwLPjOm07l+lMr09R6yXTJihtoqCgREUm+Bz9nghYzzoKr/9cM/eDLNjezBt6oikUh0n3EkD6d/c8HDvPT1QAt+8yjo8asF+6E1v392/NmQeVpUFgJG/8Mm++CZa/jmd1TAbj5jJksnjq5g+1DDW10xBpHLfF5IMvnoZChbzy/67w5/OudG3l0yyHKt/7KbOLKb8CqtyWlzcnW3hPh03dt4JGt/YGsLJ9NaW6AmrzLOa/1VrJ768n+0VI4/T1w8echOz+NLZ6YblxTxZXffZpDrb385z+28j9vWJnuJkm6eP1QPDvdrZCJLr8CZp4N2+4xWZvHCVw4jstvnj8AwBevXsrbzpo1Xq3s01fnYow9iCe6K5ZNpSDLx6+e288n/rSeqYVZrJ5ZnO5miYjICdi2ZYb9m5LHvCl5x1zPcVyaukPUtQXZUd/JvRtreXpXE1/822bOmltKRcHxMyRFxkKBCxERSa76zbDnMbB9cMOPzLBOx+LxgqcQskY4Rn4kCO3V0NNihqGKdEPeVKg6zfTmB8idAs/fhrP5rzy/5yYAzl9QNsof6uRWkOXj+29ZxRu++AxTrRacrCLsFW9Md7OGFIzEeNsvXmRTTTte2+K6U6dz69mzWVFZ2J9ds+Un8M//gubd8MIPoXotvPth00Nchi0/y8e3bjqVN/30ee7ZUMtHL11AVXFOupslIhPZtFNM4KJ+43FXe35vMwdbeijM9nHj6qpxapwcy5euWUp1Sw+ba9vxawx0EZFJxbYtyvOzKM/PYuWMIl6/upLX/+g5Nh5q549rq/nYZQvS3USZxBS4EBGR5ErUPph74fGDFmPhy4KyE5wgLb0enr8Na/cjhMPXA14WVBy7J4kcn89jMy0QBiCSO41AIkCUYb5y71Y21bRTkuvnN+86Y+jC0ctugKWvg92PwZ23Qs3LsO7XcNq7xr29E90Zc0r4j+uXc/bcUgUtRGTspsYzt+qOH7h4eX8rAJcsLifbr6Bzunlsi+/dvIqOYIRphdnpbo6IiKSQ12PzrnPn8PE/reeuddV85JL5k274Zckc6g4hIiLJdeBZM511bnrbUXka5JZjhTo4zd4BoF6AY1SRFQEg5MlNc0uG9tL+Fv6w9iAAt928auigRYJlwYLL4KLPmufr/zAOLZycbjlrFvPLFRQUkSSYdoqZNu+CSO8xV9tU0wbAKVUjzNiUlMkNeBW0EBE5SVyxbCp5AS/VLb28Wt2a7ubIJKY7OCIikjyuCweeM/PpDlzYtikeDZxlb8XnsQbVf5CRq/CbwEXQysye9YnioDeuruKc+cMcFiz+GaFp55HVuEVEZLzlVYA/D1wH2g8dc7WNh9oBWHG8ALWIiIikRLbfw8WLywF4dFtjmlsjk5kCFyIikjz1m6CnGXw5MH1VulsDs03w5Cx7Gz5lW4xZqc8MFdVjZWYBtr2HuwA4d37p8N9UMs9Mg23msysiIuljWVBQaeY7aoZcpaEjSGNnCNuCpdMLxrFxIiIiknDZEhO4+KcCF5JCuosjIiLJs+cxM51zAXj96W0LwOzzATjV2k2eHUlzYya+El8IgE43M4eC2N/cDcCcshEMZeXPgcKZZr5pVwpaJSIiI1IYD1y0Dx242HvYHOtnleaS41fJRhERkXS4cOEUPLbFjoZOqlt60t0cmaQUuBARkeTZHQ9czLs0ve1IKJlLzF9AwIoyy9OU7tZMeEUeE7jocDIv46I7FKWhw7RvRIELgLLLine truncated
"text/plain": [
"<pyannote.core.feature.SlidingWindowFeature>"
"<pyannote.core.feature.SlidingWindowFeature at 0x16adb5700>"
]
},
"execution_count": null,
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
@@ -250,7 +259,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 10,
"metadata": {},
"outputs": [
{
@@ -259,7 +268,7 @@
"(11, 293, 3)"
]
},
"execution_count": null,
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
@@ -279,7 +288,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 11,
"metadata": {},
"outputs": [
{
@@ -305,17 +314,17 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 12,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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 truncated
"image/png": "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 truncated
"text/plain": [
"<pyannote.core.feature.SlidingWindowFeature>"
"<pyannote.core.feature.SlidingWindowFeature at 0x29765eb50>"
]
},
"execution_count": null,
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
@@ -336,17 +345,17 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 13,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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 truncated
"image/png": "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 truncated
"text/plain": [
"<pyannote.core.feature.SlidingWindowFeature>"
"<pyannote.core.feature.SlidingWindowFeature at 0x2b2f9c8b0>"
]
},
"execution_count": null,
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
@@ -356,13 +365,71 @@
"output = inference.crop(AUDIO_FILE, Segment(10, 20))\n",
"output"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Offline use\n",
"\n",
"Gating models allows [me](https://herve.niderb.fr) to know a bit more about `pyannote.audio` user base and eventually help me write grant proposals to make `pyannote.audio` even better. Please fill this form as precisely as possible. \n",
"\n",
"For instance, before gating `pyannote/segmentation`, I had no idea that so many people were relying on it in production. Hint: sponsors are more than welcome! maintaining open source libraries is time consuming.\n",
"\n",
"That being said: this whole authentication process does not prevent you from using official `pyannote.audio` models offline (i.e. without going through the authentication process in every `docker run ...` or whatever you are using in production).\n",
"\n",
"* Step 1: download the `pytorch_model.bin` model\n",
"\n",
"![](assets/download-model.png)\n",
"\n",
"* Step 2: load the model"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"# look ma: no hands! \n",
"offline_model = Model.from_pretrained(\"pytorch_model.bin\")"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
"# just checking weights are the same...\n",
"import torch\n",
"for weights, offline_weights in zip(model.parameters(), offline_model.parameters()):\n",
" assert torch.equal(weights, offline_weights)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"display_name": "Python 3.9.13 ('pyannote-mps')",
"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"
},
"vscode": {
"interpreter": {
"hash": "36a3a48a52702f18671693adf589423ec3f7db45d50f6ee539f1b0696bb58d43"
}
}
},
"nbformat": 4,
+141 -45
View File
@@ -19,25 +19,24 @@
"source": [
"## Loading pipeline from 🤗 hub\n",
"\n",
"Pretrained pipelines are available on [🤗 Huggingface model hub](https://hf.co/models?other=pyannote-audio-pipeline) and can be listed by looking for the [`pyannote-audio-pipeline`](https://hf.co/models?other=pyannote-audio-pipeline) tag."
"A bunch of pretrained pipelines are available on [🤗 Huggingface model hub](https://hf.co/models?other=pyannote-audio-pipeline) and can be listed by looking for the [`pyannote-audio-pipeline`](https://hf.co/models?other=pyannote-audio-pipeline) tag."
]
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['pyannote/speaker-diarization',\n",
"['pyannote/overlapped-speech-detection',\n",
" 'pyannote/speaker-diarization',\n",
" 'pyannote/speaker-segmentation',\n",
" 'pyannote/voice-activity-detection',\n",
" 'pyannote/overlapped-speech-detection',\n",
" 'philschmid/pyannote-speaker-diarization-endpoint']"
" 'pyannote/voice-activity-detection']"
]
},
"execution_count": null,
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
@@ -45,35 +44,36 @@
"source": [
"from huggingface_hub import HfApi\n",
"available_pipelines = [p.modelId for p in HfApi().list_models(filter=\"pyannote-audio-pipeline\")]\n",
"available_pipelines"
"list(filter(lambda p: p.startswith(\"pyannote/\"), available_pipelines))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"To load the speaker diarization pipeline,\n",
"Official [pyannote.audio](https://github.com/pyannote/pyannote-audio) pipelines (i.e. those under the [`pyannote` organization](https://hf.co/pyannote) umbrella) are open-source, but gated. It means that you have to first accept users conditions on their respective Huggingface page to access the pretrained weights and hyper-parameters. Despite this initial process, those pipelines can perfectly be downloaded for later offline use: keep reading this tutorial until the end to learn how to do that.\n",
"\n",
"* accept the user conditions on [hf.co/pyannote/speaker-diarization](https://hf.co/pyannote/speaker-diarization).\n",
"* login using `notebook_login` below"
"For instance, to load the speaker diarization pipeline used in this tutorial, you have to visit [hf.co/pyannote/speaker-diarization](https://hf.co/pyannote/speaker-diarization), accept the terms, visit [hf.co/pyannote/segmentation](https://hf.co/pyannote/segmentation) (used internally by the speaker diarization pipeline), accept the terms, and log in using `notebook_login` below:"
]
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Login successful\n",
"Your token has been saved to /Users/hbredin/.huggingface/token\n",
"\u001b[1m\u001b[31mAuthenticated through git-credential store but this isn't the helper defined on your machine.\n",
"You might have to re-authenticate when pushing to the Hugging Face Hub. Run the following command in your terminal in case you want to set this credential helper as the default\n",
"\n",
"git config --global credential.helper store\u001b[0m\n"
]
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "9466934e67254fe6a7ff67b727a3f3ab",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
@@ -81,9 +81,16 @@
"notebook_login()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Once authenticated, you can load the pipeline (and the internal models)..."
]
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
@@ -110,7 +117,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
@@ -130,7 +137,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
@@ -147,7 +154,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 8,
"metadata": {},
"outputs": [
{
@@ -155,12 +162,12 @@
"output_type": "stream",
"text": [
" 6.7 7.1 SPEAKER_02\n",
" 6.9 8.3 SPEAKER_00\n",
" 7.6 8.3 SPEAKER_00\n",
" 8.3 14.8 SPEAKER_02\n",
" 9.8 11.0 SPEAKER_00\n",
"14.3 18.5 SPEAKER_01\n",
"17.9 21.5 SPEAKER_02\n",
"21.7 28.6 SPEAKER_01\n",
"14.3 18.5 SPEAKER_00\n",
"17.9 21.5 SPEAKER_01\n",
"21.7 28.6 SPEAKER_00\n",
"27.8 29.5 SPEAKER_02\n"
]
}
@@ -179,17 +186,17 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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 truncated
"image/png": "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 truncated
"text/plain": [
"<pyannote.core.annotation.Annotation>"
"<pyannote.core.annotation.Annotation at 0x285261280>"
]
},
"execution_count": null,
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
@@ -210,17 +217,17 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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 truncated
"image/png": "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 truncated
"text/plain": [
"<pyannote.core.annotation.Annotation>"
"<pyannote.core.annotation.Annotation at 0x288b56df0>"
]
},
"execution_count": null,
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
@@ -245,7 +252,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 11,
"metadata": {},
"outputs": [
{
@@ -271,32 +278,121 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 12,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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 truncated
"image/png": "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 truncated
"text/plain": [
"<pyannote.core.annotation.Annotation>"
"<pyannote.core.annotation.Annotation at 0x288d4db80>"
]
},
"execution_count": null,
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"vad = Pipeline.from_pretrained(\"pyannote/voice-activity-detection\")\n",
"vad = Pipeline.from_pretrained(\"pyannote/voice-activity-detection\", use_auth_token=True)\n",
"vad(audio_in_memory)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Offline use\n",
"\n",
"Gating models and pipelines allows [me](https://herve.niderb.fr) to know a bit more about `pyannote.audio` user base and eventually help me write grant proposals to make `pyannote.audio` even better. Please fill this form as precisely as possible. \n",
"\n",
"For instance, before gating `pyannote/speaker-diarization`, I had no idea that so many people were relying on it in production. Hint: sponsors are more than welcome! maintaining open source libraries is time consuming.\n",
"\n",
"That being said: this whole authentication process does not prevent you from using official `pyannote.audio` models and pipelines offline (i.e. without going through the authentication process in every `docker run ...` or whatever you are using in production).\n",
"\n",
"* Step 1: download `config.yaml` of [`pyannote/voice-activity-detection`](https://hf.co/pyannote/voice-activity-detection) pipeline\n",
"\n",
"![](assets/download-pipeline.png)\n",
"\n",
"* Step 2: download the `pytorch_model.bin` model\n",
"\n",
"![](assets/download-model.png)\n",
"\n",
"* Step 3: edit `config.yaml` to point to the local model\n",
"\n",
"```diff\n",
"pipeline:\n",
" name: pyannote.audio.pipelines.VoiceActivityDetection\n",
" params:\n",
"- segmentation: pyannote/segmentation@Interspeech2021\n",
"+ segmentation: pytorch_model.bin\n",
"\n",
"params:\n",
" min_duration_off: 0.09791355693027545\n",
" min_duration_on: 0.05537587440407595\n",
" offset: 0.4806866463041527\n",
" onset: 0.8104268538848918\n",
"```\n",
"\n",
"* Step 4: load the pipeline"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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 truncated
"text/plain": [
"<pyannote.core.annotation.Annotation at 0x288d1e940>"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# look ma: no hands!\n",
"offline_vad = Pipeline.from_pretrained(\"config.yaml\")\n",
"offline_vad(audio_in_memory)"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [],
"source": [
"# just checking output is the same\n",
"assert (vad(audio_in_memory) == offline_vad(audio_in_memory))"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"display_name": "Python 3.9.13 ('pyannote-mps')",
"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"
},
"vscode": {
"interpreter": {
"hash": "36a3a48a52702f18671693adf589423ec3f7db45d50f6ee539f1b0696bb58d43"
}
}
},
"nbformat": 4,
Binary file not shown.

After

Width:  |  Height:  |  Size: 471 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 376 KiB