Thien Nguyen

Overthrow4232

AI & ML interests

None yet

Recent Activity

reacted to hexgrad's post with 🔥 about 1 month ago

Wanted: Peak Data. I'm collecting audio data to train another TTS model: + AVM data: ChatGPT Advanced Voice Mode audio & text from source + Professional audio: Permissive (CC0, Apache, MIT, CC-BY) This audio should *impress* most native speakers, not just barely pass their audio Turing tests. Professional-caliber means S or A-tier, not your average bloke off the street. Traditional TTS may not make the cut. Absolutely no low-fi microphone recordings like Common Voice. The bar is much higher than last time, so there are no timelines yet and I expect it may take longer to collect such mythical data. Raising the bar means evicting quite a bit of old data, and voice/language availability may decrease. The theme is *quality* over quantity. I would rather have 1 hour of A/S-tier than 100 hours of mid data. I have nothing to offer but the north star of a future Apache 2.0 TTS model, so prefer data that you *already have* and costs you *nothing extra* to send. Additionally, *all* the new data may be used to construct public, Apache 2.0 voicepacks, and if that arrangement doesn't work for you, no need to send any audio. Last time I asked for horses; now I'm asking for unicorns. As of writing this post, I've currently got a few English & Chinese unicorns, but there is plenty of room in the stable. Find me over on Discord at `rzvzn`: https://discord.gg/QuGxSWBfQy

liked a model 2 months ago

hexgrad/Kokoro-82M

updated a model 3 months ago

Overthrow4232/punkt

View all activity

Organizations

Overthrow4232's activity

liked a model 2 months ago

hexgrad/Kokoro-82M

Text-to-Speech • Updated 14 days ago • 1.58M • 3.7k

liked a model 8 months ago

NovaSearch/stella_en_400M_v5

liked a Space 10 months ago

543

Vision Arena (Testing VLMs side-by-side)

🖼

Analyze images to detect and label objects

liked a model 10 months ago

IEITYuan/Yuan2-M32-hf

Text Generation • Updated May 30, 2024 • 344 • 60

liked a Space about 1 year ago

713

UGI Leaderboard

📢

Uncensored General Intelligence Leaderboard

liked a model about 1 year ago

avsolatorio/GIST-small-Embedding-v0

liked a Space about 1 year ago

199

Canary 1b

🐤

Transcribe and translate audio into text

liked 4 models about 1 year ago

liked 2 Spaces over 1 year ago

435

Can Ai Code Results

🏆

Generate animated avatars from images

12.8k

Open LLM Leaderboard

🏆

Track, rank and evaluate open LLMs and chatbots

liked a Space almost 2 years ago

Herta So Vits

🦀