afrideva's picture

afrideva

afrideva

·

afri_deva

AI & ML interests

None yet

Recent Activity

reacted to hexgrad's post with 👍 17 days ago

I wrote an article about G2P: https://hf.co/blog/hexgrad/g2p G2P is an underrated piece of small TTS models, like offensive linemen who do a bunch of work and get no credit. Instead of relying on explicit G2P, larger speech models implicitly learn this task by eating many thousands of hours of audio data. They often use a 500M+ parameter LLM at the front to predict latent audio tokens over a learned codebook, then decode these tokens into audio. Kokoro instead relies on G2P preprocessing, is 82M parameters, and thus needs less audio to learn. Because of this, we can cherrypick high fidelity audio for training data, and deliver solid speech for those voices. In turn, this excellent audio quality & lack of background noise helps explain why Kokoro is very competitive in single-voice TTS Arenas.

reacted to davanstrien's post with ❤️ 24 days ago

Why choose between strong LLM reasoning and efficient models? Use DeepSeek to generate high-quality training data, then distil that knowledge into ModernBERT https://huggingface.co/answerdotai/ModernBERT-base for fast, efficient classification. Blog post: https://danielvanstrien.xyz/posts/2025/deepseek/distil-deepseek-modernbert.html

liked a model 27 days ago

deepseek-ai/Janus-Pro-1B

View all activity

Organizations

afrideva's activity

New activity in afrideva/gemma-1.1-2b-it_oasst_format_chatML_unsloth_V1_function_calling_V2-GGUF 10 months ago

good model!!!

#1 opened 10 months ago by

New activity in afrideva/phi-2-sft-dpo-gpt4_en-ep1-GGUF about 1 year ago

GGUF conversion

#1 opened about 1 year ago by

New activity in afrideva/Mixtral-GQA-400m-v2-GGUF about 1 year ago

Format Chat ml?

#1 opened about 1 year ago by

New activity in Yhyu13/phi-2-sft-alpaca_gpt4_en-ep1 about 1 year ago

Quant pls

#1 opened about 1 year ago by

New activity in Aryanne/Astrohermes-3B about 1 year ago

Safetensors model file name

#1 opened about 1 year ago by

New activity in afrideva/TinyKAI-3B-beta-GGUF about 1 year ago

Thank you!

#1 opened over 1 year ago by

New activity in afrideva/MiniChat-3B-GGUF about 1 year ago

question about command line to convert

#1 opened about 1 year ago by

New activity in afrideva/evolvedSeeker_1_3-GGUF about 1 year ago

llama.cpp is working fine with the models

#1 opened over 1 year ago by

New activity in afrideva/trained-tinyllama-ultrachat-GGUF over 1 year ago

stable

#1 opened over 1 year ago by

New activity in afrideva/Tiny-Llama-openhermes-1.1B-step-715k-1.5T-GGUF over 1 year ago

question

#1 opened over 1 year ago by

question

#1 opened over 1 year ago by

question

#1 opened over 1 year ago by