Add Colab example (#67)

Thank you @HarishDevLab for the suggestion, I just reimplemented the PR
to link to a version-controlled notebook.

README.md

@@ -59,6 +59,8 @@ for each voice.
 * [azelma](https://huggingface.co/kyutai/tts-voices/blob/main/vctk/p303_023.wav)
 
 The `--voice` argument can also take a plain wav file as input for voice cloning.
+You can use your own or check out our [voice repository](https://huggingface.co/kyutai/tts-voices).
+
 Feel free to check out the [generate documentation](https://github.com/kyutai-labs/pocket-tts/tree/main/docs/generate.md) for more details and examples.
 For trying multiple voices and prompts quickly, prefer using the `serve` command.
 
@@ -76,6 +78,8 @@ You can check out the [serve documentation](https://github.com/kyutai-labs/pocke
 
 ## Using it as a Python library
 
+You can try out the Python library on Colab [here](https://colab.research.google.com/github/kyutai-labs/pocket-tts/blob/main/docs/pocket-tts-example.ipynb).
+
 Install the package with
 ```bash
 pip install pocket-tts
@@ -90,7 +94,10 @@ import scipy.io.wavfile
 
 tts_model = TTSModel.load_model()
 voice_state = tts_model.get_state_for_audio_prompt(
-    "hf://kyutai/tts-voices/alba-mackenna/casual.wav"
+    "alba"  # One of the pre-made voices, see above
+    # You can also use any voice file you have locally or from Hugging Face:
+    # "./some_audio.wav"
+    # or "hf://kyutai/tts-voices/expresso/ex01-ex02_default_001_channel2_198s.wav"
 )
 audio = tts_model.generate_audio(voice_state, "Hello world, this is a test.")
 # Audio is a 1D torch tensor containing PCM data.

docs/pocket-tts-example.ipynb

@@ -0,0 +1,80 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "OiFxAw6MoHnp"
+   },
+   "outputs": [],
+   "source": [
+    "# Locally, we recommend using `uv` over `pip`\n",
+    "!pip install pocket-tts"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "FfBHOrFcU0gI"
+   },
+   "outputs": [],
+   "source": [
+    "import scipy.io.wavfile\n",
+    "from IPython.display import Audio\n",
+    "\n",
+    "from pocket_tts import TTSModel\n",
+    "\n",
+    "# The pre-defined voices are alba, marius, javert, jean, fantine, cosette, eponine, and azelma.\n",
+    "# You can also clone any voice you'd like by passing a file path!\n",
+    "# For voice cloning, please go to https://huggingface.co/kyutai/pocket-tts\n",
+    "# and accept the terms, then make sure you're logged in locally with `uvx hf auth login`.\n",
+    "voice = \"alba\"\n",
+    "\n",
+    "tts_model = TTSModel.load_model()\n",
+    "voice_state = tts_model.get_state_for_audio_prompt(voice)\n",
+    "\n",
+    "# Audio is a 1D torch tensor containing PCM data\n",
+    "audio = tts_model.generate_audio(voice_state, \"Hello world, this is a test.\")\n",
+    "\n",
+    "# You can also find the output in the files tab on the left\n",
+    "scipy.io.wavfile.write(\"output.wav\", tts_model.sample_rate, audio.numpy())\n",
+    "\n",
+    "Audio(audio.numpy(), rate=tts_model.sample_rate)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "gbnHfLwbo5W8"
+   },
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "pocket-tts",
+   "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": "3.10.16"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}