Update README.md

README.md

@@ -4,7 +4,7 @@ language:
   - th
 library_name: nemo
 pipeline_tag: automatic-speech-recognition
-base_model: typhoon-ai/typhoon-asr-realtime
+base_model: scb10x/typhoon-asr-realtime
 tags:
   - automatic-speech-recognition
   - speech
@@ -18,15 +18,12 @@ tags:
 # Typhoon ASR Streaming 115M
 
 Cache-aware **streaming** Thai ASR (FastConformer-Transducer, 115M params). Converted from
-[Typhoon ASR Real-time](https://huggingface.co/typhoon-ai/typhoon-asr-realtime) — causal
+[Typhoon ASR Real-time](https://huggingface.co/scb10x/typhoon-asr-realtime) — causal
 convolutions + chunked limited-context attention swapped in, every weight copied as a warm
 start, then briefly fine-tuned on the ~11k-hour Thai corpus. Unlike the full-context base
 (which collapses to 62.8% CER when forced to stream at 1040 ms), this model decodes live,
 chunk by chunk, with the encoder cache carried across chunks.
 
-Companion model to the paper *Typhoon ASR Streaming: Steerable Low-Latency Thai Speech
-Recognition with Real-Time Shallow Fusion* (SCB DataX). Code, demo, and evaluation suite:
-[github.com/warit-s/typhoon-asr-streaming](https://github.com/warit-s/typhoon-asr-streaming).
 
 ## At a glance
 
@@ -72,7 +69,7 @@ streaming decoder — see the repo's `docs/SHALLOW_FUSION.md`.
 
 Released under **CC-BY-4.0**, following the base-model chain:
 
-- fine-tuned + converted from **[typhoon-ai/typhoon-asr-realtime](https://huggingface.co/typhoon-ai/typhoon-asr-realtime)** (CC-BY-4.0, SCB DataX),
+- fine-tuned + converted from **[scb10x/typhoon-asr-realtime](https://huggingface.co/scb10x/typhoon-asr-realtime)** (CC-BY-4.0, SCB DataX),
 - itself fine-tuned from **[nvidia/stt_en_fastconformer_transducer_large](https://huggingface.co/nvidia/stt_en_fastconformer_transducer_large)** (CC-BY-4.0, NVIDIA).
 
 Modifications in this release: full-context → cache-aware streaming conversion (causal