Running
on
L4
33
⚡
Talk To Ultravox
Talk to Fixie.ai's Ultravox with WebRTC ⚡️
Aidy Osu
aidystark
AI & ML interests
Vision;Language;Speech
Recent Activity
liked
a Space
5 days ago
freddyaboulton/talk-to-ultravox
liked
a Space
6 days ago
fishaudio/fish-speech-1
liked
a model
18 days ago
Qwen/Qwen2-VL-7B-Instruct
Organizations
aidystark's activity
liked
a
Space
5 days ago
liked
a
Space
6 days ago
liked
a
model
18 days ago
liked
a
model
20 days ago
reacted to
merve's
post with 🚀
22 days ago
Post
2630
small but mighty 🔥
you can fine-tune SmolVLM on an L4 with batch size of 4 and it will only take 16.4 GB VRAM 🫰🏻 also with gradient accumulation simulated batch size is 16 ✨
I made a notebook that includes all the goodies: QLoRA, gradient accumulation, gradient checkpointing with explanations on how they work 💝 https://github.com/huggingface/smollm/blob/main/finetuning/Smol_VLM_FT.ipynb
you can fine-tune SmolVLM on an L4 with batch size of 4 and it will only take 16.4 GB VRAM 🫰🏻 also with gradient accumulation simulated batch size is 16 ✨
I made a notebook that includes all the goodies: QLoRA, gradient accumulation, gradient checkpointing with explanations on how they work 💝 https://github.com/huggingface/smollm/blob/main/finetuning/Smol_VLM_FT.ipynb
liked
a
model
about 1 month ago
upvoted
a
collection
about 1 month ago
liked
a
Space
about 1 month ago
liked
a
model
about 1 month ago
liked
a
Space
about 2 months ago
Thanks very much for the resource
I will reach out
updated
a
dataset
2 months ago
liked
a
Space
3 months ago
liked
a
model
3 months ago
reacted to
fdaudens's
post with 🧠👍
3 months ago
Post
995
🚀 OpenAI's new Whisper "turbo": 8x faster, 40% VRAM efficient, minimal accuracy loss.
🔒 Run it locally in-browser for private transcriptions! Transcribe interviews, audio & video.
⚡️ 40 tokens/sec on my MacBook
🔗 Try it: webml-community/whisper-large-v3-turbo-webgpu
Model: https://huggingface.co./ylacombe/whisper-large-v3-turbo
🔒 Run it locally in-browser for private transcriptions! Transcribe interviews, audio & video.
⚡️ 40 tokens/sec on my MacBook
🔗 Try it: webml-community/whisper-large-v3-turbo-webgpu
Model: https://huggingface.co./ylacombe/whisper-large-v3-turbo
liked
a
Space
3 months ago
Okay...
The Language is spoken in Africa (Nigeria) but it is part of the Niger Congo Language Family it is called "Ibibio". We are just capturing the language for the first time digitally . We will try to get it to 60k Hours for a start. What i saw was that if the language is not captured in Flan T5 then the training of Parler TTS should be done from scratch; what's your intuition on this.
reacted to
PHBJT's
post with 🔥
3 months ago
Post
1764
Bringing Open-Source Text-to-Speech to French! 🗣️🇫🇷
Hugging Face's Parler TTS mini can now speak French! 🇫🇷🎉
You can try it here: PHBJT/french_parler_tts
Key highlights:
Transform the English TTS model to speak French 🇬🇧➡️🇫🇷
Fully open source (code, weights, and datasets) 🛠️
It can be replicated for every language 🌍
Read more about it in this article: https://huggingface.co./blog/PHBJT/french-parler-tts
Special thanks to FlexAI and their dedicated team for providing the computing power that made this possible and of course to all of the Parler TTS community 🤗
Hugging Face's Parler TTS mini can now speak French! 🇫🇷🎉
You can try it here: PHBJT/french_parler_tts
Key highlights:
Transform the English TTS model to speak French 🇬🇧➡️🇫🇷
Fully open source (code, weights, and datasets) 🛠️
It can be replicated for every language 🌍
Read more about it in this article: https://huggingface.co./blog/PHBJT/french-parler-tts
Special thanks to FlexAI and their dedicated team for providing the computing power that made this possible and of course to all of the Parler TTS community 🤗
-
- 8 replies