AI Model2026
An instruction‑tuned Gemma 4 E4B multimodal model on Hugging Face that accepts text, images and audio and generates text; notable for 128K long context support, built-in thinking mode, and an on‑device‑friendly E4B architecture under an Apache‑2.0 license.
AI Dataset2026
Provides a unified 615k-hour English speech corpus for TTS training, aggregating 11 public datasets and web-sourced recordings into 16 kHz Opus WebDataset shards. Includes a quality-filtered core subset (510.1k hours), metadata splits, and mixed licenses across sources.
AI Dataset2026
Provides 3,000+ hours (≈611K utterances) of transcribed 16 kHz multi-dialect Arabic speech across 13 dialects for ASR and spoken-dialect identification. Transcripts preserve dialectal orthography (partial diacritics); the train split is ~337 GB in parquet, so streaming is recommended.
AI Model2026
Converts text to natural-sounding speech across 600+ languages in a zero-shot way, with short-reference voice cloning and fine-grained voice-design controls; uses a diffusion language-model-style architecture to balance quality and very low inference latency.
AI Audio2026
Zero-shot text-to-speech across 600+ languages with short-reference voice cloning and attribute-based voice design. Uses a diffusion-style discrete non-autoregressive architecture mapping text to multi-codebook acoustic tokens, supports phoneme/pinyin control and very low RTF.
AI Audio2026
Runs local speech-to-text inference for a wide range of ASR model families using GGUF models on the ggml runtime. Supports Metal, Vulkan, and CUDA GPU backends plus a tinyBLAS-accelerated CPU path, prebuilt GGUFs on Hugging Face, and a quantization tool.
AI Audio2026
Desktop app for local voice cloning, real-time dictation, and end-to-end video dubbing using zero-shot TTS across 600+ languages; features multi-engine TTS/ASR, speaker diarization, vocal isolation, batch pipelines, and invisible audio watermarking — all run fully offline.
AI Audio2026
Generates expressive, prompt-driven text-to-speech audio with optional 10-second voice cloning; prompts control speaker identity, emotion, pauses and nonverbal sounds. An IC‑LoRA fine-tune of LTX‑2.3 that applies an imperceptible Resemble Perth watermark.
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 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 Model2026
Multilingual 2B speech–language model for ASR and bidirectional speech translation (EN, FR, DE, ES, PT, JA), providing punctuation/truecasing, keyword biasing, and a dual-head CTC encoder to boost transcription accuracy.
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.