Update README

README.md

@@ -17,15 +17,6 @@ BayLing-Duplex is a native full-duplex speech dialogue model. It listens and spe
 
 BayLing-Duplex represents user speech, assistant text, and assistant speech as a single multi-channel interleaved autoregressive sequence. Turn-taking, interruption handling, text planning, and speech-token generation are all expressed as next-token prediction.
 
-The default released layout uses a `10:5:10` interleave ratio:
-
-```text
-Block b:
-  user speech tokens       x[bN : (b+1)N]
-  assistant text tokens    z[bM : (b+1)M]
-  assistant speech tokens  y[bN : (b+1)N]
-```
-
 The text channel carries dialogue-state tokens such as `[SILENCE]`, `<|assistant|>`, `[PAD]`, and `[EPAD]`, so no extra classifier head, VAD, scheduler, or finite-state turn-taking controller is required at inference time.
 
 ## Highlights
@@ -33,7 +24,6 @@ The text channel carries dialogue-state tokens such as `[SILENCE]`, `<|assistant
 - Native full-duplex speech dialogue: the model can listen while speaking.
 - Single autoregressive decoding path for timing decisions, text, and speech tokens.
 - Block-wise multi-channel interleaving that preserves contiguous assistant text.
-- Minimal `BayLingDuplex` Python API and CLI for model loading, tokenization, decoding, and audio synthesis.
 
 ## Model Weights
 
@@ -46,13 +36,13 @@ pip install -U huggingface_hub
 hf auth login
 
 mkdir -p models
-HF_ENDPOINT=https://huggingface.co hf download BayLing-Models/BayLing-Duplex \
+hf download BayLing-Models/BayLing-Duplex \
   --repo-type model \
   --local-dir models/bayling_duplex_model
-HF_ENDPOINT=https://huggingface.co hf download zai-org/glm-4-voice-tokenizer \
+hf download zai-org/glm-4-voice-tokenizer \
   --repo-type model \
   --local-dir models/speech_tokenizer
-HF_ENDPOINT=https://huggingface.co hf download zai-org/glm-4-voice-decoder \
+hf download zai-org/glm-4-voice-decoder \
   --repo-type model \
   --local-dir models/speech_decoder
 ```
@@ -162,7 +152,7 @@ See [LICENSE](LICENSE) and [NOTICE.md](NOTICE.md).
 ```bibtex
 @misc{baylingduplextbd,
   title        = {BayLing-Duplex: Native Full-Duplex Speech Dialogue with a Single Autoregressive LLM},
-  author       = {{BayLing-Duplex Team}},
+  author       = {Qingkai Fang and Shoutao Guo and Yang Feng},
   year         = {2026},
   note         = {Manuscript}
 }