Audio Samples for RTVC-1 Voice Cloning Model

Repository: CorentinJ/Real-Time-Voice-Cloning @5425557

Description: RTVC-1 consists of the original pretrained models released with the Real-Time-Voice-Cloning repository. RTVC-1 output may contain very long pauses. This is resolved in RTVC-3 with better data preprocessing.

Click here for more voice cloning experiments.

RTVC-1 Model Overview

Name Model Steps Batch Size Datasets Used Speakers Audio Duration
Speaker Encoder: Pretrained GE2E 1,564,501 64 LibriSpeech train-other-500
VoxCeleb1 Dev A-D
VoxCeleb2 Dev A-H
8371 3201 hours
Synthesizer: Pretrained Tacotron 2 278,000 144 LibriSpeech train-clean-100
LibriSpeech train-clean-360
1172 436 hours
Vocoder: Pretrained WaveRNN 428,000 100 LibriSpeech train-clean-100
LibriSpeech train-clean-360
1172 436 hours

Voice Cloning Results

All speakers are unseen during training. The first row is the reference audio used to compute the speaker embedding. The rows below that are synthesized using that speaker embedding.

VCTK p240VCTK p260LibriSpeech 1320LibriSpeech 3575LibriSpeech 6829LibriSpeech 8230
Reference:
 
Synthesized:
0: Take a look at these pages for crooked creek drive.
Google:
RTVC-1:
 
1: There are several listings for gas station.
Google:
RTVC-1:
 
2: Here's the forecast for the next four days.
Google:
RTVC-1:
 
3: Here is some information about the Gospel of John.
Google:
RTVC-1:
 
4: His motives were more pragmatic and political.
Google:
RTVC-1:
 
5: She had three brothers and two sisters.
Google:
RTVC-1:
 
6: This work reflects a quest for lost identity, a recuperation of an unknown past.
Google:
RTVC-1:
 
7: There were many editions of these works still being used in the nineteenth century.
Google:
RTVC-1:
 
8: Modern birds are classified as coelurosaurs by nearly all palaeontologists.
Google:
RTVC-1:
 
9: He was being fitted for ruling the state, in the words of his biographer.
Google:
RTVC-1: