51 15 354

Smoliakov PRO

Yehor

https://t.me/doing_something

AI & ML interests

Speech-to-Text, Text-to-Speech, Voice over Internet Protocol

Recent Activity

reacted to leonardlin's post with 👍 about 11 hours ago

Happy to announce the release of Shisa V2, our latest generation of our bilingual Japanese-English language models. After hundreds of ablations and months of work, we're releasing some of the strongest open Japanese models at 7B, 8B, 12B, 14B, 32B and 70B! Full announcement here https://shisa.ai/posts/shisa-v2/ or visit the Shisa V2 HF collection: https://huggingface.co/collections/shisa-ai/shisa-v2-67fc98ecaf940ad6c49f5689

updated a model about 21 hours ago

Yehor/w2v-bert-uk-v2.1_onnx-gpu_op14_fp32

published a model about 21 hours ago

Yehor/w2v-bert-uk-v2.1_onnx-gpu_op14_fp32

View all activity

Organizations

Yehor's activity

reacted to leonardlin's post with 👍 about 11 hours ago

Post

939

replied to their post 2 days ago

Also, tested it on A100 with TensorRT:

https://colab.research.google.com/drive/1-agoo5ll-hWEecWQAtO1FM39sqavJxph?usp=sharing

Results are not so obvious, but it works base_rfdetr_fp16.onnx model and gives ~10ms/img

posted an update 3 days ago

Post

2571

I have made a Rust project with integration of the latest state-of-the-art model for object detection, it outperforms YOLO!

Check it out: https://github.com/egorsmkv/rf-detr-usls

2 replies

replied to their post 7 days ago

This program does what datasets does. When you push dataset created by the audiofolder script, it creates parquet data and shard them internally.

So, you can use audios-to-dataset instead if you need faster speeds than datasets provides.

posted an update 7 days ago

Post

2047

Convert your audio data to Parquet/DuckDB files with blazingly fast speeds!

Repository with pre-built binaries: https://github.com/crs-org/audios-to-dataset

2 replies

replied to their post 9 days ago

My channel in Telegram: https://t.me/doing_something

posted an update 9 days ago

Post

2229

Create spectrogram using Rust!

Slightly improved nice project that creates spectrogram and built binaries for different platform using cross-rs I've mentioned earlier in my channel.

Repo: https://github.com/crs-org/sonogram

1 reply

replied to their post 12 days ago

Tested the tool on Windows, it works as expected. It's now more easier to work with audio data than before!

posted an update 12 days ago

Post

653

Added more built executables to extract-audio I've released recently.

See my previous post - https://huggingface.co/posts/Yehor/654118712490771

Repository: https://github.com/crs-org/extract-audio

1 reply

posted an update 14 days ago

Post

1928

Made a simple Python script to generate Argilla project for audio annotation from a dataset:

https://github.com/egorsmkv/argilla-audio-annotation

1 reply

posted an update 16 days ago

Post

2040

Are you interesting in different runtimes for AI models?

Check out IREE (iree.dev), it convert models to MLIR and then execute on different platforms.

I have tested it in Rust on CPU and CUDA: https://github.com/egorsmkv/eerie-yolo11

replied to their post 21 days ago

See a demo: https://colab.research.google.com/drive/1prztEZIf8nNFUSaptY8Jv16VO8Crjnzb?usp=sharing

posted an update 21 days ago

Post

2224

Extract audio datasets with Rust on blazingly fast speeds!

With this tool you can extract audio files from a parquet or arrow file generated by Hugging Face datasets library.

Repository: https://github.com/egorsmkv/extract-audio

1 reply

posted an update about 1 month ago

Post

617

If you spent a lot of time in Telegram, then use this bot to monitor state of your ML lab:

https://github.com/egorsmkv/gpu-state-tgbot

reacted to clem's post with 🤗 about 1 month ago

Post

4634

We just crossed 1,500,000 public models on Hugging Face (and 500k spaces, 330k datasets, 50k papers). One new repository is created every 15 seconds. Congratulations all!

3 replies

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

Post

1650

Google just dropped an exciting technical report for the brand-new Gemma3 model! 🚀 Here are my personal notes highlighting the most intriguing architectural innovations, design choices, and insights from this release:

1) Architecture choices:
> No more softcaping, replace by QK-Norm
> Both Pre AND Post Norm
> Wider MLP than Qwen2.5, ~ same depth
> SWA with 5:1 and 1024 (very small and cool ablation on the paper!)
> No MLA to save KV cache, SWA do the job!

2) Long context
> Only increase the rope in the global layer (to 1M)
> Confirmation that it's harder to do long context for smol models, no 128k for the 1B
> Pretrained with 32k context? seems very high
> No yarn nor llama3 like rope extension

3) Distillation
> Only keep te first 256 logits for the teacher
> Ablation on the teacher gap (tl;dr you need some "patience" to see that using a small teacher is better)
> On policy distillation yeahh (by
@agarwl_
et al), not sure if the teacher gap behave the same here, curious if someone have more info?

4) Others
> Checkpoint with QAT, that's very cool
> RL using improve version of BOND, WARM/WARP good excuse to look at
@ramealexandre
papers
> Only use Zero3, no TP/PP if i understand correctly ?
> Training budget relatively similar than gemma2

1 reply

reacted to tomaarsen's post with 👍 about 1 month ago

Post

6651

An assembly of 18 European companies, labs, and universities have banded together to launch 🇪🇺 EuroBERT! It's a state-of-the-art multilingual encoder for 15 European languages, designed to be finetuned for retrieval, classification, etc.

🇪🇺 15 Languages: English, French, German, Spanish, Chinese, Italian, Russian, Polish, Portuguese, Japanese, Vietnamese, Dutch, Arabic, Turkish, Hindi
3️⃣ 3 model sizes: 210M, 610M, and 2.1B parameters - very very useful sizes in my opinion
➡️ Sequence length of 8192 tokens! Nice to see these higher sequence lengths for encoders becoming more common.
⚙️ Architecture based on Llama, but with bi-directional (non-causal) attention to turn it into an encoder. Flash Attention 2 is supported.
🔥 A new Pareto frontier (stronger *and* smaller) for multilingual encoder models
📊 Evaluated against mDeBERTa, mGTE, XLM-RoBERTa for Retrieval, Classification, and Regression (after finetuning for each task separately): EuroBERT punches way above its weight.
📝 Detailed paper with all details, incl. data: FineWeb for English and CulturaX for multilingual data, The Stack v2 and Proof-Pile-2 for code.

Check out the release blogpost here: https://huggingface.co/blog/EuroBERT/release
* EuroBERT/EuroBERT-210m
* EuroBERT/EuroBERT-610m
* EuroBERT/EuroBERT-2.1B

The next step is for researchers to build upon the 3 EuroBERT base models and publish strong retrieval, zero-shot classification, etc. models for all to use. I'm very much looking forward to it!

1 reply

replied to their post about 1 month ago

Also, the Q&A dataset:

https://huggingface.co/datasets/ua-l/questions-with-answers

posted an update about 1 month ago

Post

1511

Published some datasets for researchers in Ukrainian NLP from my project https://ua-lawyer.com (Q&A platform in Ukraine):

Datasets:
- ua-l/topics
- ua-l/topics-train-test
- ua-l/topics-text-label

Model:
- https://huggingface.co/ua-l/topics-classifier

Space:
- ua-l/topics-classifier-demo

1 reply

posted an update about 1 month ago

Post

2874

Published a stable version of Ukrainian Text-to-Speech library on GitHub and PyPI.

Features:

- Multi-speaker model: 2 female (Tetiana, Lada) + 1 male (Mykyta) voices;
- Fine-grained control over speech parameters, including duration, fundamental frequency (F0), and energy;
- High-fidelity speech generation using the RAD-TTS++ acoustic model;
- Fast vocoding using Vocos;
- Synthesizes long sentences effectively;
- Supports a sampling rate of 44.1 kHz;
- Tested on Linux environments and Windows/WSL;
- Python API (requires Python 3.9 or later);
- CUDA-enabled for GPU acceleration.

Repository: https://github.com/egorsmkv/tts_uk