TTS Arena: Benchmarking Text-to-Speech Models in the Wild
•
42
mrfakename PRO
mrfakename
AI & ML interests
LLMs, TTS, & Open Source
Recent Activity
updated
a Space
about 9 hours ago
mrfakename/E2-F5-TTS
updated
a Space
about 21 hours ago
TTS-AGI/TTS-Arena
new activity
about 22 hours ago
TTS-AGI/TTS-Arena:Add Kokoro, the #1🥇 TTS Model in TTS-Spaces-Arena 🏆 with only 82M params 🤏
Articles
Organizations
Posts
10
Post
5978
I just released an unofficial demo for Moonshine ASR!
Moonshine is a fast, efficient, & accurate ASR model released by Useful Sensors. It's designed for on-device inference and licensed under the MIT license!
HF Space (unofficial demo): mrfakename/Moonshine
GitHub repo for Moonshine: https://github.com/usefulsensors/moonshine
Moonshine is a fast, efficient, & accurate ASR model released by Useful Sensors. It's designed for on-device inference and licensed under the MIT license!
HF Space (unofficial demo): mrfakename/Moonshine
GitHub repo for Moonshine: https://github.com/usefulsensors/moonshine
Post
9913
Introducing StyleTTS 2 detector, an audio classification model to detect StyleTTS 2 vs human-generated content!
Dual-licensed under MIT/Apache 2.0.
Model Weights: mrfakename/styletts2-detector
Spaces: mrfakename/styletts2-detector
Dual-licensed under MIT/Apache 2.0.
Model Weights: mrfakename/styletts2-detector
Spaces: mrfakename/styletts2-detector
Collections
3
Projects I've worked on
TTS models that support zero-shot voice cloning
-
MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer
Paper • 2409.00750 • Published • 3 -
F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching
Paper • 2410.06885 • Published • 43 -
StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion
Paper • 2409.10058 • Published • 1 -
E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS
Paper • 2406.18009 • Published • 20
spaces
25
pinned
Running
on
Zero
1.54k
🗣️
F5-TTS
F5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)
pinned
Running
10
🤔
Did StyleTTS 2 Generate It?
Did StyleTTS 2 generate that audio?!?
pinned
Running
21
🔊
seewav-gui
pinned
Running
on
Zero
3
📄
TB-OCR Demo
Unofficial demo for TB-OCR (OCR for documents)
pinned
Running
on
Zero
35
🌒
Moonshine ASR
Fast & efficient ASR outperforming Whisper!
pinned
Running
on
Zero
399
🖼️
OpenDalle V1.1 GPU Demo
A demo of OpenDalle V1.1 on a ZERO GPU.
models
8
mrfakename/train_test_step1
Text Generation
•
Updated
mrfakename/CosyVoice2-0.5B
Updated
mrfakename/experimental-model-base
Updated
mrfakename/styletts2-detector-turbo
Audio Classification
•
Updated
•
12
•
1
mrfakename/styletts2-detector
Audio Classification
•
Updated
•
18
•
2
mrfakename/llamaphi-3-128k-instruct
Text Generation
•
Updated
•
11
•
1
mrfakename/refusal
Text Generation
•
Updated
•
25
•
6
mrfakename/deep-phonemizer
Updated
datasets
16
mrfakename/noisy-speech-files
Preview
•
Updated
•
1.41k
mrfakename/datablend
Viewer
•
Updated
•
299k
•
25
mrfakename/identity
Viewer
•
Updated
•
1k
•
41
•
1
mrfakename/noisy-speech
Updated
•
36
mrfakename/librivox-files
Preview
•
Updated
•
1
mrfakename/pdmx-multi-instrument-synthesized
Viewer
•
Updated
•
24.4k
•
5
mrfakename/basic-math-1m
Viewer
•
Updated
•
1,000k
•
65
•
3
mrfakename/basic-math-10m
Viewer
•
Updated
•
10M
•
86
•
3
mrfakename/refusal
Viewer
•
Updated
•
3.86k
•
59
•
4
mrfakename/MATH
Viewer
•
Updated
•
12.5k
•
10
•
3