Document unified EchoLoc code and checkpoints repository

CHECKPOINTS.md

@@ -0,0 +1,24 @@
+# Released Checkpoints
+
+The checkpoints below are the model artifacts used for the reported best EchoLoc Thinker+Talker evaluation. They are stored in this repository under `checkpoints/` and are separate from the source-only `MANIFEST.tsv`.
+
+## Thinker
+
+- Repository path: `checkpoints/thinker/`
+- Training artifact: Iter006 `latest_final_model`
+- Format: PEFT LoRA adapter with tokenizer and processor assets
+- Base model: `Qwen/Qwen3-Omni-30B-A3B-Instruct`
+- Main file: `adapter_model.safetensors`
+- Size: `4,642,233,208` bytes
+- SHA-256: `cf716ae5bb40a49ef75f642229a0e7ca74e381925e21c66f8d161aa128514ac2`
+
+## Talker
+
+- Repository path: `checkpoints/talker/`
+- Training artifact: `qwen3omni_talker_vstyle_46000`
+- Format: Talker state dictionary with tokenizer assets
+- Main file: `pytorch_model.bin`
+- Size: `3,833,490,035` bytes
+- SHA-256: `cd1e07334a94b59f827f55c6805b80a3ac8e0ed9b9c92217590ede712783b335`
+
+The Talker loader first initializes the merged Qwen3-TTS Base/VoiceDesign origin and then loads this state dictionary into the inner Talker. See `checkpoints/talker/README.md` and `RUNBOOK.md` for the exact commands.

MANIFEST.tsv

@@ -12,6 +12,7 @@ calibration_agent/supervisor/settings.py	5459	66dea00fe354a21acd5e070e4af8e04777
 calibration_agent/supervisor/simple_agent.py	69263	0331facf2bbc4d0621f9bbee4f9ec13a14411ca0756d75ced33b3dd02989f712
 calibration_agent/supervisor/store.py	1241	8cdaa0ab421d49f67ec28846ee92de0a840a238cb9782029d2ab123c03a3754a
 calibration_agent/supervisor/ui.py	27801	2dc34cda0deb6ba99442ccce825fa9bace466f86f386406844e8033fd6d44490
+CHECKPOINTS.md	1130	d2e2ff26797795c176963814db732f057a03573e8392821d0f54dfcd8689b40e
 data_construction/add_iter006_english_prompts.py	20797	8f88f28f019a491abdf432eca6ee4387219c88328f3556ae0a26dc95db50b62d
 data_construction/audit_wav_clipping.py	2086	51f66c9466d4738ae300a0b652a48ac673e82ace13539119e34b65c217036653
 data_construction/build_thinker_sft_data.py	7898	7245fbd8b65c449b0b9c96247cb86ac3384d1a0e9faa8891cc19b3e0b883b8b6
@@ -227,7 +228,7 @@ model/thinker_talker/examples/qwen3omni_thinker/train_simple.sh	992	5ae961f75df2
 model/thinker_talker/models/qwen3_tts/core/models/modeling_qwen3_tts.py	152204	4aa5583b4cce5d8ee54069474424cbf26fc4acca7d977fb36e14324efa18b83a
 model/thinker_talker/models/qwen3_tts/inference/qwen3_tts_model.py	42661	96b16a4a7a855d32322310fa721e6fa3dd0ee755e049f6511db91b149c64d21f
 model/thinker_talker/models/qwen3omni/model.py	14892	38f2ca200ae0361708584522a63e0043eb135d472720d69197f8f99d0c00ee8e
-README.md	2186	c0481fe0bcd8ec95cf78471c64b5f523bfb3f321206874767be317dcdfe91860
+README.md	2635	df2f6d87f48c383b569707a1f951068c00177693c32e2f11d0b5d1f6212593e7
 rendering/universal_tts/configs/cosyvoice2.yaml	3507	895db6dc291c1ca2c4e3bb0327097e84f447eb6d68063403ea20200dc7efd0df
 rendering/universal_tts/configs/defaults.yaml	920	1224660c8c09d3c9a09ac4555845c18040acf9f108fb318dd64c848c9a8ba21f
 rendering/universal_tts/configs/ds_zero2.json	533	3f5cf0247bc119d502aa487f0d27186fd24bfa3b02dfc3834c2ec4b53772ccf8

README.md

@@ -14,12 +14,18 @@ Large datasets, generated audio, cached features, job logs, API credentials, and
 
 ## Released checkpoints
 
-- Thinker PEFT adapter: `zsy814/EchoLoc-Thinker`
-- Talker checkpoint: `zsy814/EchoLoc-Talker`
+- Thinker PEFT adapter: `checkpoints/thinker/`
+- Talker checkpoint: `checkpoints/talker/`
 - Thinker base: `Qwen/Qwen3-Omni-30B-A3B-Instruct`
 - Talker origins: `Qwen/Qwen3-TTS-12Hz-1.7B-Base` and `Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign`
 
-The Talker checkpoint is loaded over the Base/VoiceDesign merged origin described in the Talker model card. The repositories are kept private during double-blind review and can be made public after anonymity restrictions are lifted.
+Download this private repository, including both checkpoints, with:
+
+```bash
+hf download zsy814/EchoLoc --local-dir echoloc-release
+```
+
+The Talker checkpoint is loaded over the Base/VoiceDesign merged origin described in `checkpoints/talker/README.md`. This repository is kept private during double-blind review and can be made public after anonymity restrictions are lifted.
 
 ## Directory map
 
@@ -32,7 +38,10 @@ The Talker checkpoint is loaded over the Base/VoiceDesign merged origin describe
 - `evaluation/render_metrics/` and `evaluation/esd/`: AutoPCP, emotion embedding, smoothness, WER, ESD alignment, and report generation.
 - `inference/benchmarks/`: generic benchmark input, Thinker/Talker inference, and output export.
 - `experiments/`: reviewer-facing statistical analyses.
+- `checkpoints/thinker/`: best Iter006 Thinker PEFT adapter and tokenizer assets.
+- `checkpoints/talker/`: best Talker-46000 state dictionary and tokenizer assets.
+- `CHECKPOINTS.md`: checkpoint provenance, byte sizes, and SHA-256 digests.
 - `SOURCE_INVENTORY.tsv`: implementation-area inventory.
-- `MANIFEST.tsv`: size and SHA-256 for every archived file.
+- `MANIFEST.tsv`: size and SHA-256 for every source-release file; checkpoint hashes are recorded separately in `CHECKPOINTS.md`.
 
 Start with `ENVIRONMENT.md`, then follow `RUNBOOK.md`. Run `python tools/validate_archive.py` for a source and manifest integrity check.