Congrats!
Smoliakov
Yehor
AI & ML interests
Speech-to-Text, Text-to-Speech, Voice over Internet Protocol
Recent Activity
updated a model 20 minutes ago
speech-uk/squeezeformer-sm-full updated a model 21 minutes ago
speech-uk/zipformer-l-test published a model about 2 hours ago
speech-uk/squeezeformer-sm-fullOrganizations
repliedto MaziyarPanahi's post 13 days ago
reactedto MaziyarPanahi's post with 🔥 13 days ago
Post
2192
We annotated 119K medical images with two frontier VLMs (Qwen 3.5, Kimi K2.5), cross-validated at 93% agreement, and produced 110K training records, all for under $500. Fine-tuning 3 small models (2-3B params) improved all benchmarks: best model reaches +15.0% average exact match.
Everything is open-sourced: datasets, adapters, and code.
https://huggingface.co/blog/OpenMed/synthvision
Everything is open-sourced: datasets, adapters, and code.
https://huggingface.co/blog/OpenMed/synthvision
- 2 replies
posted an update 3 months ago
Post
399
A useful tool for all who works with audio datasets: https://github.com/RustedBytes/data-viewer-audio
reactedto mitkox's post with 🔥 6 months ago
Post
2848
Say hello to my little friends! I just unboxed this trio of HP Z2 G1a!
Three is always better than one!
3x AMD Ryzen AI Max+ Pro 395
384GB RAM
24TB of RAID storage
Ubuntu 24.04
ROCm 7.0.2
llama cpp, vLLM and Aibrix
Small, cheap GPUs are about to become the Raspberry Pi of edge AI inference. Sprinkle some
Make sure you own your AI. AI in the cloud is not aligned with you; it’s aligned with the company that owns it.
Three is always better than one!
3x AMD Ryzen AI Max+ Pro 395
384GB RAM
24TB of RAID storage
Ubuntu 24.04
ROCm 7.0.2
llama cpp, vLLM and Aibrix
Small, cheap GPUs are about to become the Raspberry Pi of edge AI inference. Sprinkle some
kubectl fairy dust on top, and suddenly it's a high-availability, self-healing, cloud-native, enterprise-grade AI cluster camping in a closet.Make sure you own your AI. AI in the cloud is not aligned with you; it’s aligned with the company that owns it.
- 3 replies
where can I try it?
repliedto their post 6 months ago
Added this tool: https://github.com/RustedBytes/audio-parquet-merger
repliedto their post 6 months ago
Now with inference on Rust: https://github.com/egorsmkv/kulyk-rust
posted an update 6 months ago
Post
286
Containerized Yehor/kulyk-en-uk and Yehor/kulyk-uk-en so you can just pull an image and run CPU-version to do machine translation:
docker run -p 3000:3000 --rm ghcr.io/egorsmkv/kulyk-rust:latestreactedto MohamedRashad's post with 👍 8 months ago
Post
3298
If someone is interested in trying the new rednote-hilab/dots.ocr model. I made this space for you:
MohamedRashad/Dots-OCR
MohamedRashad/Dots-OCR
- 2 replies
repliedto their post 9 months ago
Added a vice versa model: from Ukrainian to English - https://huggingface.co/spaces/Yehor/uk-en-translator
repliedto their post 9 months ago
This comment has been hidden
repliedto their post 9 months ago
This comment has been hidden
posted an update 9 months ago
Post
770
A new lightweight model to do machine translation from English to Ukrainian using recently published LFM2 model. Use demo Yehor/en-uk-translator to test it.
Facts:
- Fine-tuned with 40M samples (filtered by quality metric) from ~53.5M for 1.4 epochs
- 354M params
- Requires 1 GB of RAM to run with bf16
- BLEU on FLORES-200: 27.24
- Tokens per second: 229.93 (bs=1), 1664.40 (bs=10), 8392.48 (bs=64)
- License: lfm1.0
Mode page: Yehor/kulyk-en-uk
Facts:
- Fine-tuned with 40M samples (filtered by quality metric) from ~53.5M for 1.4 epochs
- 354M params
- Requires 1 GB of RAM to run with bf16
- BLEU on FLORES-200: 27.24
- Tokens per second: 229.93 (bs=1), 1664.40 (bs=10), 8392.48 (bs=64)
- License: lfm1.0
Mode page: Yehor/kulyk-en-uk
- 5 replies
posted an update 12 months ago
Post
967
Esoteric practices: inference models in PHP!
Repository: https://github.com/egorsmkv/speech-to-text-using-php
Repository: https://github.com/egorsmkv/speech-to-text-using-php
posted an update 12 months ago
Post
2513
Made a workable program that uses IREE runtime using Rust to inference wav2vec2-bert model for Automatic Speech Recognition.
- 1 reply
reactedto leonardlin's post with 👍 12 months ago
Post
2707
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: shisa-ai/shisa-v2-67fc98ecaf940ad6c49f5689
repliedto their post 12 months 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 about 1 year ago
Post
2708
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
Check it out: https://github.com/egorsmkv/rf-detr-usls
- 2 replies