filmov
tv
Voice Swap using NVIDIA's NeMo on Python | GPU 3080 TI giveaway announcement | GTC'22
Показать описание
✅ Step 2: Wait for the GTC to start and join the Keynote livestream.
✅ Step 3: Attend GTC sessions. NOTE: Prizes will be awarded only to those who register for GTC using the link above and attend some sessions.
✅ Step 4: Subscribe to my YouTube channel.
The event will include Jensen’s news-filled, live-streamed keynote on March 22 at 15:00 GMT and 16:00 EST and will be available on demand afterward.
This GTC will focus on accelerated computing, deep learning, data science, digital twins, networking, quantum computing and computing in the data center, cloud and edge. There will be more than 20 dedicated sessions on how AI can help visualize and further climate science. You can read more about GTC in this press release.
📚📚About
In this tutorial, we will build a voice swap python app on Google Colab, called VoiceSwap with the help of the powerful conversational AI toolkit, NeMo and conversational AI pre-trained AI models, such as QuartzNet for automatic speech recognition, FastPitch for spectrogram generation, and HifiGAN for our Vocoder model. The app reads generic voice audio samples and converts (or swaps) them to a computer generated one.
⏲⏲Outline
00:00 Intro
00:29 GPU Giveaway Announcement
00:38 Steps to take part in Giveaway
04:02 What is NeMo ?
05:47 Checking the GPU
06:08 Installing NeMo
07:13 Downloading an audio sample
07:56 Instantiating pre-trained AI models
10:17 Convert Audio to Text
11:59 Text to Audio
13:03 Voice swap
14:07 Outro
CREDITS x MENTIONS:
📚📚 MY FREE ONLINE COURSES:
📚📚 OTHER RECOMMENDED COURSES
BE MY FRIEND:
WHO AM I:
GET IN TOUCH:
I try my best to respond to each and every comment here on YouTube, you guys are my family ❤️
#GTC22 #AI #nemo
✅ Step 3: Attend GTC sessions. NOTE: Prizes will be awarded only to those who register for GTC using the link above and attend some sessions.
✅ Step 4: Subscribe to my YouTube channel.
The event will include Jensen’s news-filled, live-streamed keynote on March 22 at 15:00 GMT and 16:00 EST and will be available on demand afterward.
This GTC will focus on accelerated computing, deep learning, data science, digital twins, networking, quantum computing and computing in the data center, cloud and edge. There will be more than 20 dedicated sessions on how AI can help visualize and further climate science. You can read more about GTC in this press release.
📚📚About
In this tutorial, we will build a voice swap python app on Google Colab, called VoiceSwap with the help of the powerful conversational AI toolkit, NeMo and conversational AI pre-trained AI models, such as QuartzNet for automatic speech recognition, FastPitch for spectrogram generation, and HifiGAN for our Vocoder model. The app reads generic voice audio samples and converts (or swaps) them to a computer generated one.
⏲⏲Outline
00:00 Intro
00:29 GPU Giveaway Announcement
00:38 Steps to take part in Giveaway
04:02 What is NeMo ?
05:47 Checking the GPU
06:08 Installing NeMo
07:13 Downloading an audio sample
07:56 Instantiating pre-trained AI models
10:17 Convert Audio to Text
11:59 Text to Audio
13:03 Voice swap
14:07 Outro
CREDITS x MENTIONS:
📚📚 MY FREE ONLINE COURSES:
📚📚 OTHER RECOMMENDED COURSES
BE MY FRIEND:
WHO AM I:
GET IN TOUCH:
I try my best to respond to each and every comment here on YouTube, you guys are my family ❤️
#GTC22 #AI #nemo
Комментарии