Add Talker-T2AV + WhisperX-VAE weights (model params only, no optimizer state)

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+talker-t2av/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,76 @@
 ---
 license: apache-2.0
+language:
+  - zh
+  - en
+tags:
+  - talking-head
+  - text-to-video
+  - audio-video-generation
+  - autoregressive
+  - diffusion
+library_name: transformers
 ---
+
+# Talker-T2AV
+
+**Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling**
+
+[Paper (arXiv 2604.23586)](https://arxiv.org/abs/2604.23586) ·
+[Code (GitHub)](https://github.com/zhenye234/Talker-T2AV) ·
+[Samples](https://talker-t2av.github.io/)
+
+This repository hosts the pretrained weights for the paper
+"Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive
+Diffusion Modeling".
+
+## Contents
+
+```
+talker-t2av/
+  model.safetensors            ← AR backbone (Qwen3-0.6B) + dual diffusion heads
+                                  + Patch Transformer Encoder + Stop Predictor
+                                  (3.12 B params, 2.77 GB)
+  config.json
+  chat_template.jinja
+  tokenizer.json
+  tokenizer_config.json
+
+whisperx-vae/
+  model.ckpt                   ← WhisperX-VAE audio autoencoder
+                                  (32-d, 25 Hz; Whisper-Large-v3 encoder + DAC backbone)
+```
+
+For the LIA-X video motion autoencoder (40-d motion, 25 Hz), see
+[wyhsirius/LIA-X](https://github.com/wyhsirius/LIA-X) — its weights are NOT
+hosted here.
+
+## Quickstart
+
+```bash
+git clone https://github.com/zhenye234/Talker-T2AV.git
+cd Talker-T2AV
+
+# put the weights in place
+huggingface-cli download HKUSTAudio/Talker-T2AV --local-dir ./hf_weights
+ln -s "$(pwd)/hf_weights/talker-t2av"  ./ckpts/checkpoint-229954
+export WHISPERVAE_CKPT="$(pwd)/hf_weights/whisperx-vae/model.ckpt"
+
+python infer.py
+```
+
+See the [GitHub README](https://github.com/zhenye234/Talker-T2AV) for full
+installation and reproduction instructions.
+
+## Citation
+
+```bibtex
+@article{ye2026talkert2av,
+  title   = {Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling},
+  author  = {Ye, Zhen and Tan, Xu and Yin, Aoxiong and Lin, Hongzhan and
+             Zhang, Guangyan and Sun, Peiwen and Li, Yiming and
+             Chan, Chi-Min and Ye, Wei and Zhang, Shikun and Xue, Wei},
+  journal = {arXiv preprint arXiv:2604.23586},
+  year    = {2026}
+}
+```

talker-t2av/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

talker-t2av/config.json

@@ -0,0 +1,63 @@
+{
+  "architectures": [
+    "SpeechLLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "float32",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.3.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

talker-t2av/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:893e130e88c03b22179dd4efba6628ed5eb3c03d1637931aedff4b78fc590dc3
+size 2770431192

talker-t2av/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:507f9cdc7200bbbf57240103221ab4ae4f888dfe5154ef245a24e6c3ec1b26b3
+size 11423312

talker-t2av/tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<SPEECH_FRAME>",
+    "<MOTION_FRAME>"
+  ],
+  "is_local": false,
+  "model_max_length": 1000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

whisperx-vae/model.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6def379348fb6b5fb716fa2187a9bc8b5a15c8beae0d2644c0ca4fe2c398d904
+size 6907516457