Pith Number

pith:QHW4BRHG

pith:2026:QHW4BRHGUTTLL6BEF223QVWJNZ

not attested not anchored not stored refs pending

Human-1 by Josh Talks: A Full-Duplex Conversational Modeling Framework in Hindi using Real-World Conversations

Bhaskar Singh, Mahima Manik, Pranav Sharma, Shobhit Banga

The first open full-duplex spoken dialogue system for Hindi learns turn-taking and overlaps directly from 26,000 hours of real conversations.

arxiv:2604.23295 v2 · 2026-04-25 · cs.CL · cs.AI

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{QHW4BRHGUTTLL6BEF223QVWJNZ}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

We present the first open, reproducible full-duplex spoken dialogue system for Hindi by adapting Moshi, a state-of-the-art duplex speech architecture, using a custom Hindi tokeniser and training on 26,000 hours of real spontaneous conversations collected from 14,695 speakers with separate speaker channels, enabling direct learning of turn-taking and overlap patterns from natural interactions.

C2weakest assumption

That reinitializing only the text-vocabulary-dependent parameters while retaining the pre-trained audio components from the English Moshi model will allow the system to effectively learn and generate natural full-duplex conversational behaviors in Hindi from the collected data.

C3one line summary

Human-1 is the first open full-duplex spoken dialogue system for Hindi, created by adapting Moshi with a custom tokenizer and training on 26,000 hours of real-world conversations to enable natural interruptions and overlaps.

Receipt and verification

First computed	2026-05-26T02:04:11.375375Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

81edc0c4e6a4e6b5f8242eb5b856c96e5f436e81c1534277ee88c6e10d3a01a3

Aliases

arxiv: 2604.23295 · arxiv_version: 2604.23295v2 · doi: 10.48550/arxiv.2604.23295 · pith_short_12: QHW4BRHGUTTL · pith_short_16: QHW4BRHGUTTLL6BE · pith_short_8: QHW4BRHG

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/QHW4BRHGUTTLL6BEF223QVWJNZ \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 81edc0c4e6a4e6b5f8242eb5b856c96e5f436e81c1534277ee88c6e10d3a01a3

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "9732cc91f0648f1a1967fe14ea052916acc8f44288feee5e52de6e48f7808319",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-04-25T13:18:40Z",
    "title_canon_sha256": "4cdc89dc61763383044d7b026a17cbfacec777d430ad4f94fe64cd639cd7b752"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.23295",
    "kind": "arxiv",
    "version": 2
  }
}