214 1 40

Ronan McGovern

RonanMcGovern

https://ronanmcgovern.com

AI & ML interests

Open source LLMs. Fine-tuning. Summarisation. Patents.

Recent Activity

updated a dataset about 10 hours ago

Trelis/atc-voxtral-confidence-stats-test

published a dataset about 10 hours ago

Trelis/atc-voxtral-confidence-stats-test

updated a dataset about 10 hours ago

Trelis/atc-voxtral-with-confidence-filter

View all activity

Organizations

posted an update 2 months ago

Post

148

🎻Custom Voice Model Training Services (STT, TTS): https://trelis.com/fine-tuning-services

-- OR --

Do it yourself with Trelis Studio (https://studio.trelis.com)

repliedto VictorSanh's post almost 2 years ago

ok, really nice, thanks

repliedto VictorSanh's post almost 2 years ago

How do you think this compares to some of the LLaVA Llama 3 models?

reactedto VictorSanh's post with ❤️ almost 2 years ago

Post

2885

Glad to see Idefics2 making its way into the awesome OpenVLM Leaderboard which ranks VLMs. 🏆
2nd in its category (<10B parameters and open weights)!

While InternLM-XComposer2 uses proprietary data, Idefics2 is built solely using openly available data.

Leaderboard: opencompass/open_vlm_leaderboard
Model: HuggingFaceM4/idefics2-8b

9 replies

reactedto nateraw's post with 👍 almost 2 years ago

Post

4575

Turns out if you do a cute little hack, you can make nateraw/musicgen-songstarter-v0.2 work on vocal inputs. 👀

Now, you can hum an idea for a song and get a music sample generated with AI 🔥🔥

Give it a try: ➡️ nateraw/singing-songstarter ⬅️

It'll take your voice and try to autotune it (because let's be real, you're no michael jackson), then pass it along to the model to condition on the melody. It works surprisingly well!

Ronan McGovern

AI & ML interests

Recent Activity

Organizations

RonanMcGovern's activity