mrfakename PRO

mrfakename

AI & ML interests

LLMs, TTS, & Open Source

Recent Activity

updated a model about 8 hours ago
MegaTTS3/aligner_lm
published a model about 8 hours ago
MegaTTS3/aligner_lm
updated a model about 8 hours ago
MegaTTS3/diffusion_transformer
View all activity

Organizations

Notebooks-explorers's profile picture Webhooks Explorers (BETA)'s profile picture Spam Block's profile picture Blog-explorers's profile picture mrfakename's profile picture TTS Models's profile picture TTS Arena's profile picture TTS Eval (OLD)'s profile picture ZeroGPU Explorers's profile picture StyleTTS 2 Demo's profile picture StyleTTS 2 Community's profile picture Unofficial Mistral Community's profile picture OpenPhonemizer's profile picture NeuralVox's profile picture ML for Speech's profile picture CSP-Data's profile picture MLX Community's profile picture Open-Weight Models's profile picture TTS AGI's profile picture Social Post Explorers's profile picture MOS's profile picture Dev Mode Explorers's profile picture OpenRLM's profile picture Hugging Face Discord Community's profile picture test's profile picture OpenMusic's profile picture RefinedSpeech's profile picture Unofficial SI Reuploads's profile picture llamafy's profile picture Speech Data's profile picture OpusLM's profile picture my test org's profile picture test org's profile picture GPUs Cloud's profile picture Unofficial model mirrors for MegaTTS 3's profile picture

mrfakename's activity

posted an update 14 days ago
posted an update 15 days ago
posted an update 2 months ago
view post
Post
2560
I’m excited to introduce a new leaderboard UI + keyboard shortcuts on the TTS Arena!

The refreshed UI for the leaderboard is smoother and (hopefully) more intuitive. You can now view models based on a simpler win-rate percentage and exclude closed models.

In addition, the TTS Arena now supports keyboard shortcuts. This should make voting much more efficient as you can now vote without clicking anything!

In both the normal Arena and Battle Mode, press "r" to select a random text, Cmd/Ctrl + Enter to synthesize, and "a"/"b" to vote! View more details about keyboard shortcuts by pressing "?" (Shift + /) on the Arena.

Check out all the new updates on the TTS Arena:

TTS-AGI/TTS-Arena
  • 1 reply
Β·
reacted to nyuuzyou's post with 🀯 4 months ago
view post
Post
2910
its over
Β·
replied to their post 4 months ago
view reply

Hi, do you see a limit in the number of voices I have 416 and it fails to load all of them. (scroll menu limit?)

I'm not sure if there's a set limit for the dropdown, but with that many voices, it might make sense to not use the dropdown but instead have a textbox to specify the path to the reference speaker.

replied to their post 4 months ago
view reply

I don't think that's supported by the model, but you could fine-tune it or clone a voice with emotions. (I am not the author of the model itself, just of the web demo)

replied to their post 4 months ago
view reply

Hi,
You can upload a WAV file to the voices folder. Then, in the app.py file, add the filename of the voice (without .wav) to the voicelist list. It should show up in the Gradio demo.

replied to their post 4 months ago
view reply

Hi,
I added:

import nltk
nltk.download('punkt_tab')

and it seems to resolve the issue for me. Have you changed any code from the original Space?
Thanks!

replied to their post 4 months ago
replied to their post 4 months ago
view reply

Hi,
Sorry about the issues! Please try adding:

nltk.download('punkt_tab')

below the nltk.download() line – let me know if it works!

posted an update 5 months ago
view post
Post
7808
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
replied to their post 6 months ago
view reply

Training itself would be pretty easy, but the main issue would be data. AFAIK there's not much data out there for other TTS models. I synthetically generated the StyleTTS 2 dataset as it's quite efficient but other models would require much more compute.

reacted to Jofthomas's post with πŸ”₯ 8 months ago
view post
Post
6435
Everchanging Quest is out !

It is an LLM controlled Rogue-Like in which the LLM gets a markdown representation of the map, and should generate a JSON with the objective to fulfill on the map as well as the necessary objects and their placements.

Come test it on the space :
Jofthomas/Everchanging-Quest
  • 2 replies
Β·
reacted to cdminix's post with πŸ‘ 9 months ago
view post
Post
2242
Since new TTS (Text-to-Speech) systems are coming out what feels like every day, and it's currently hard to compare them, my latest project has focused on doing just that.

I was inspired by the TTS-AGI/TTS-Arena (definitely check it out if you haven't), which compares recent TTS system using crowdsourced A/B testing.

I wanted to see if we can also do a similar evaluation with objective metrics and it's now available here:
ttsds/benchmark
Anyone can submit a new TTS model, and I hope this can provide a way to get some information on which areas models perform well or poorly in.

The paper with all the details is available here: https://arxiv.org/abs/2407.12707
replied to not-lain's post 9 months ago
reacted to not-lain's post with πŸ€— 9 months ago
view post
Post
7746
I am now a huggingface fellow πŸ₯³
Β·
reacted to lunarflu's post with πŸ”₯ 10 months ago
view post
Post
1992
cooking up something....anyone interested in a daily activity tracker for HF?
Β·
posted an update 11 months ago
replied to their post 11 months ago
view reply

@mahiatlinux is correct. But it can also be used if you have a classification filter and need an explanation on why a message is blocked.

replied to KingNish's post 11 months ago
view reply

I don’t think so, it’s the same model just without image generation