AI Dataset2026
Benchmarks ASR on long-form English call-center conversations with wide accent coverage; 128.6 hours across 14 accent groups and 16 service domains, designed for segmentation-sensitive evaluation and intended for evaluation/analysis (CC BY‑SA 4.0).
AI Model2026
Provides a lightweight assistant (draft) model for Gemma 4 E4B used in speculative-decoding pipelines — it predicts token drafts that the target model verifies in parallel, enabling up to ~2× decoding speedups while preserving identical final outputs. Useful for low-latency, multimodal assistant and on-device scenarios.
AI Model2026
Unifies video, audio, image and text understanding for enterprise Q&A, summarization, transcription and document intelligence. The NVFP4 quantized variant reduces footprint to ~20.9GB for more efficient single‑GPU deployment and is tuned for NVIDIA runtimes (vLLM, TensorRT).
AI Audio2026
Generates expressive, scene-aware speech from XML-style prompts and supports zero-shot voice cloning from 10–20s references. Produces emotional acting, ambient SFX, multilingual output, and continuous long-form narration; requires large model weights and gated Gemma text-encoder access.
AI Model2026
Unified omnimodal foundation model for text, image, video and audio understanding and agentic workflows, with support for up to 1M-token context. Combines a sparse MoE LLM backbone, dedicated vision/audio encoders, multi-token prediction, and a hybrid sliding-window + global attention design to reduce KV-cache overhead.
AI Model2026
Provides a GGUF-quantized build of NVIDIA's Nemotron 3 Nano Omni 30B (Reasoning) for local inference — enables multimodal (video/audio/image/text) reasoning, transcription, and document understanding on compatible runtimes such as llama.cpp, Ollama, vLLM, and TensorRT-LLM.
AI Dataset2026
Provides 100 English–Khasi parallel sentence pairs with aligned studio-quality WAV recordings for ASR, TTS and translation evaluation; curated by Medharvix as a restricted public sample—full corpus available by request.
AI Dataset2026
Provides 55 million scene-level video clips (each with captions, language labels, and timestamps) extracted from an 80M-video, 10-million-hour raw pool to support multimodal pre-training across video, audio, and frames. Access is gated for academic/non-commercial research.
AI Audio2026
Converts text into natural-sounding speech locally using compact ONNX TTS assets. Optimized for CPU/edge inference (~99M params) with support for 31 languages, expression tags (e.g., <laugh>), and improved stability versus Supertonic 2 — suitable for on-device multilingual TTS.
AI Dataset2026
Provides tick-aligned Counter-Strike 2 player POV video clips with per-tick inputs and world-state sidecars — near-lossless 1280×720@32fps video, per-player stereo audio, and parquet indexes for event/kill/round filtering; suited for RL, video classification and clip mining.
AI Audio2026
Generates high-quality Japanese speech from text with zero-shot voice cloning and emoji-based style controls; uses a flow-matching diffusion transformer over DACVAE continuous latents, includes a duration predictor and integrated SilentCipher watermarking. Japanese-only.
AI Audio2026
Generates music, sound effects, and general audio from text prompts using a medium-size Stable Audio 3 diffusion model — a balance of generation quality and inference cost suitable for prototyping, demo assets, and creative sound design workflows.