vineeth_k
March 19, 2019, 2:18pm
1
My goal is to build a speaker recognition system(i.e., verifying if a person is who he claims he is, with his voice).
Where do I start?
tbass134
November 5, 2019, 3:56pm
2
Have a look into the Fast AI Audio Thread
I’ve found very little audio content on the forums, so I thought I’d start a thread for all things audio where we can post resources, find people working on similar projects, and help each other out. Maybe we could get a separate study group or slack/telegram chat going as well. Note: I am early in fast.ai and have only studied the audio->image->CNN route, if anyone else has experience with using RNNs in audio, please help contribute some resources.
Fast.ai specific
FastAI Audio V2 - Current…
This notebook should help as well
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 10 Speakers with new API\n",
"\n",
"A demonstration of using fastai with audio.\n",
"\n",
"Generating spectrograms with, as of (May 2019), some good transformations to help reduce overfitting."
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"%reload_ext autoreload\n",
show original
1 Like
EMEliasMi8859
December 8, 2025, 5:23am
4
so you can start by creating a GUI like web app or a desktop app using anything you want but i recomment streamlit or qt for fast development and then use speechbrain’s ECAPA-TDNN trained with voxceleb pretrianed model which has both speaker identification and speaker verification so you would have an entire self hosted app which works wouth local apis