replace audio sample, update overview in readme.md

README.md

@@ -21,7 +21,7 @@ Sample audio encoded with `Qwen/Qwen3-TTS-Tokenizer-12Hz` and decoded with both
 
 | | Audio |
 |---|---|
-| Original<br/>[Voice material by “Amitaro’s Voice Material Studio”](https://amitaro.net/) | <audio controls><source src="https://huggingface.co/takuma104/Qwen3-TTS-Tokenizer-12Hz-48kHz/resolve/main/assets/original.wav" type="audio/wav"></audio> |
+| Original<br/>[Hi-Fi-CAPTAIN (CC BY-NC-SA 4.0)](https://ast-astrec.nict.go.jp/release/hi-fi-captain/) | <audio controls><source src="https://huggingface.co/takuma104/Qwen3-TTS-Tokenizer-12Hz-48kHz/resolve/main/assets/original.wav" type="audio/wav"></audio> |
 | Reconstructed 24 kHz (base model) | <audio controls><source src="https://huggingface.co/takuma104/Qwen3-TTS-Tokenizer-12Hz-48kHz/resolve/main/assets/reconstructed_24k.wav" type="audio/wav"></audio> |
 | Reconstructed 48 kHz (this model) | <audio controls><source src="https://huggingface.co/takuma104/Qwen3-TTS-Tokenizer-12Hz-48kHz/resolve/main/assets/reconstructed_48k.wav" type="audio/wav"></audio> |
 
@@ -31,9 +31,7 @@ Sample audio encoded with `Qwen/Qwen3-TTS-Tokenizer-12Hz` and decoded with both
 
 ## Overview
 
-The original Qwen3-TTS-Tokenizer-12Hz decoder outputs audio at 24 kHz. This model extends it by appending one additional `DecoderBlock` (upsample rate ×2) to the existing decoder stack, effectively doubling the output sample rate to 48 kHz.
-
-Because the modification is purely a config change (`upsample_rates: [8,5,4,3] → [8,5,4,3,2]`), the model retains the standard `model_type: qwen3_tts_tokenizer_12hz` and can be loaded with the upstream `transformers` library without `trust_remote_code=True`.
+In the HuggingFace ecosystem, model weights are always distributed with a `config.json` that defines the architecture; `transformers` dynamically instantiates the model graph from these parameters before loading the weights — and Qwen3-TTS fully adheres to this convention. Its 12 Hz codec decoder performs 1920× upsampling (12.5 Hz × 1920 = 24 kHz) governed by the `upsample_rates` list in `config.json`. This 48 kHz variant achieves double the output sample rate purely by appending `2` to that list (`[8, 5, 4, 3] → [8, 5, 4, 3, 2]`), letting `transformers` instantiate one additional `DecoderBlock` at load time — no code changes required.
 
 **Key properties:**
 
@@ -145,7 +143,8 @@ The three new modules at the end (~95K parameters) are randomly initialized. The
 
 ## Training Code
 
-https://github.com/takuma104/Qwen3-TTS-Experimental/blob/decoder_block_48k/finetuning/decoder_block_48k/train_gan.sh
+- Obsolete: [The training code for currently release model weight](https://github.com/takuma104/Qwen3-TTS-Experimental/blob/decoder_block_48k/finetuning/decoder_block_48k/train_gan.sh) 
+- New codebase: https://github.com/takuma104/Qwen3-TTS-Tokenizer-12Hz-Trainer
 
 ## Training Logs
 

assets/original.wav

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a5475679d1a68109c5abea2ab72f172856f3f105880dd9ccbe402e9334bf4d0
-size 413856
+oid sha256:d2a8cd996aec5926c6d24a0961f1cb9acd54a027dc440b7bfa4fc4a88b549534
+size 520218

assets/reconstructed_24k.wav

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adb8d5dbe43d69c9a8634c8c03f38ae6c1662588d2b7600f8b99ff5f25613acb
-size 207404
+oid sha256:2ec116f89139a22cb07323cbf799034be6363fe276680af0ac6b332e51d5627e
+size 261164

assets/reconstructed_48k.wav

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a9d2055880b76e452dcfcee4634b3d7c40d18d493d87b9c759ca4809e8c190c
-size 414764
+oid sha256:6ef04427a931fed062442c2e0954f634486a082be5ff6cc96995e330bfcad601
+size 522284