Update README.md
Browse files
README.md
CHANGED
|
@@ -16,7 +16,7 @@ pipeline_tag: audio-to-audio
|
|
| 16 |
---
|
| 17 |
|
| 18 |
# Human-1: A Full-Duplex Conversational Model for Hindi
|
| 19 |
-
**🎙️ [Try the live demo →](https://ai.joshtalks.com/research/human-1)** | **📄 [Paper →](https://
|
| 20 |
|
| 21 |
Human-1 by Josh Talks is the first full-duplex spoken dialogue model for Hindi, built by adapting [Kyutai's Moshi](https://github.com/kyutai-labs/moshi) architecture. It enables real-time, natural Hindi conversation with support for interruptions, overlaps, backchannels, and natural turn-taking — trained on 26,000 hours of real spontaneous Hindi conversations from 14,695 speakers.
|
| 22 |
|
|
|
|
| 16 |
---
|
| 17 |
|
| 18 |
# Human-1: A Full-Duplex Conversational Model for Hindi
|
| 19 |
+
**🎙️ [Try the live demo →](https://ai.joshtalks.com/research/human-1)** | **📄 [Paper →](https://arxiv.org/pdf/2604.23295v1)**
|
| 20 |
|
| 21 |
Human-1 by Josh Talks is the first full-duplex spoken dialogue model for Hindi, built by adapting [Kyutai's Moshi](https://github.com/kyutai-labs/moshi) architecture. It enables real-time, natural Hindi conversation with support for interruptions, overlaps, backchannels, and natural turn-taking — trained on 26,000 hours of real spontaneous Hindi conversations from 14,695 speakers.
|
| 22 |
|