Everything built for the Kashmiri language, in one place
Kashmiri research is scattered across arXiv, HuggingFace, government portals and university PDFs — which makes it hard to know what already exists, and easy to rebuild something twice. This is a single, tracked catalogue of 205 datasets, papers, models, tools and the groups behind them, spanning 1932–2026.
Where the effort is going
Resource count by task. The long tail is the interesting part — it shows which problems in Kashmiri NLP are still essentially untouched.
Bolbosh — Kashmiri TTS
Script-aware flow-matching TTS purpose-built for Kashmiri, with a 272-grapheme vocabulary covering the language's diacritics and vowel distinctions. Current state of the art for Kashmiri speech synthesis at MOS 3.63.
Bolbosh: Script-Aware Flow Matching for Kashmiri Text-to-Speech
A new benchmark for Kashmiri speech synthesis. Uses Optimal Transport Conditional Flow Matching within a Matcha-TTS architecture, expanding the vocabulary to 272 graphemes to model Kashmiri diacritics and fine-grained vowel distinctions explicitly. Achieves MOS 3.63 and MCD 3.73, substantially outperforming multilingual baselines.
Bolbosh — TTS code
Open-source code for Bolbosh, the Kashmiri text-to-speech framework from Gaash Lab, NIT Srinagar.
Bolbosh Kashmiri TTS Dataset — Gaash Lab
About 40,000 Kashmiri utterances with transcripts (33,182 train, 4,542 validation, 2,272 test) curated from IndicVoices-R and RASA for text-to-speech; the training data behind Bolbosh. Mostly spontaneous speech; the RASA part keeps its original licence.
Chaashini
Continuously growing corpus of clean, single-speaker, studio-grade speech in 33 Indian languages (about 2,955 hours), each clip passed through a multi-stage quality gate. Includes Kashmiri.
Gemini 3.8 Flash TTS — Kashmiri
Google's Gemini text-to-speech model lists Kashmiri in both Perso-Arabic and Devanagari script.
KTTS Single Speaker Dataset (Kashmiri TTS)
Structured redistribution of the KTTS single-speaker corpus: 2,984 recordings by one male native speaker at 48 kHz with aligned Perso-Arabic transcriptions, for training and evaluating TTS.
Matcha-TTS Kashmiri — Gaash Lab
A Kashmiri text-to-speech model based on Matcha-TTS, from Gaash Lab, NIT Srinagar.
Yemberzal TTS — Kashmiri
Kashmiri text-to-speech from kenpath/svara-tts-v1 (Llama-3.2-3B with SNAC audio tokens), trained on IndicVoices-R then RASA. The card reports 37.6% WER from an ASR transcriber whose floor on real speech is 36.5%.
Indic Parler-TTS
Multilingual text-to-speech model covering Indian languages with reported support for Kashmiri. Provides a general-purpose TTS baseline that Kashmiri-specific systems such as Bolbosh are measured against.
Rasa — Expressive TTS
Expressive multilingual text-to-speech dataset for Indian languages, targeting at least 20 hours per speaker with a female and a male voice per language. Kashmiri is included. Funded by Bhashini (MeitY).
UrduSpeech — Urdu & Kashmiri Speech Corpus
Multi-style, professionally recorded speech corpus covering Urdu and Kashmiri, designed for both text-to-speech and automatic speech recognition.
YODAS2-Sidon
Version of the YouTube-derived YODAS-2 corpus cleaned with the Sidon speech-restoration model for speech synthesis and spoken language modelling. Has a Kashmiri subset.
IndicVoices-R — Kashmiri
Speech-synthesis-oriented release derived from IndicVoices, with a Kashmiri split of mostly spontaneous recordings.
Kashmiri TTS Dataset (HNM)
Kashmiri speech with transcripts prepared for text-to-speech training.
AI4Bharat
The most significant producer of open Indic language technology. Behind IndicTrans2, the BPCC corpora, IndicBERT, IndicConformer ASR and Indic Parler-TTS — most of the general-purpose models that currently support Kashmiri at all.
NIT Srinagar — Language & Systems Research
Engineering research base in the Valley. Contributed the Bolbosh Kashmiri TTS system in collaboration with the University of Kashmir, currently the strongest Kashmiri speech synthesis result.
Bhasini — National Language Translation Mission
Official Indian government AI platform with Kashmiri translation, ASR, and TTS APIs. Free to use for developers. Includes models for all 22 scheduled languages.
Something missing?
This hub is only useful if it stays current. If you have built a Kashmiri dataset, model, tool, or published a paper — or you know of one that is not listed — send it over. Submissions are reviewed before they appear.
Showing the bundled catalogue — the live database is not reachable right now.