Add Audio8-TTS-Preview-0.6b MLX conversion (bf16 LM + fp32 codec, arktts)

.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,77 @@
+---
+license: apache-2.0
+base_model: Audio8/Audio8-TTS-Preview-0.6b
+library_name: mlx-audio
+pipeline_tag: text-to-speech
+language:
+  - yue
+  - zh
+  - nl
+  - en
+  - fr
+  - de
+  - it
+  - ja
+  - ko
+  - pl
+  - es
+tags:
+  - mlx
+  - audio
+  - text-to-speech
+  - tts
+  - voice-cloning
+  - zero-shot
+  - multilingual
+  - arktts
+---
+
+# Audio8-TTS-Preview-0.6b-bf16 (MLX)
+
+MLX conversion of [Audio8/Audio8-TTS-Preview-0.6b](https://huggingface.co/Audio8/Audio8-TTS-Preview-0.6b)
+(revision `1b17c91`) for Apple Silicon — a 0.6B-parameter multilingual text-to-speech
+model with zero-shot voice cloning and a bundled 44.1 kHz neural codec.
+
+- **Language model**: bf16 (as published upstream)
+- **Codec**: fp32, converted from `codec.pth` to safetensors with weight-norm folded
+  and conv weights in MLX (channels-last) layout
+- **Architecture**: `arktts` — a DualAR transformer (24-layer slow AR predicting one
+  semantic token per frame, 4-layer fast AR predicting 10 codec codebooks per frame),
+  inspired by Fish Audio S2 Pro
+
+Conversion parity vs the PyTorch reference (fp32, CPU): unit/block outputs within
+1e-4, reference-audio codec encoding 100% code-exact, greedy generation 100%
+token-exact over the validation utterance, decoded waveform max-abs 7.5e-6.
+
+## Usage (mlx-audio)
+
+Requires an [mlx-audio](https://github.com/Blaizzy/mlx-audio) version with `arktts`
+support.
+
+```python
+import soundfile as sf
+from mlx_audio.tts.utils import load
+
+model = load("mlx-community/Audio8-TTS-Preview-0.6b-bf16")
+
+# zero-shot voice cloning: the reference transcript must match the reference audio
+for result in model.generate(
+    text="Welcome to Audio8 TTS, running on Apple Silicon.",
+    ref_audio="reference.wav",
+    ref_text="Transcript of the reference clip.",
+    temperature=0.7, top_p=0.9, top_k=50,
+):
+    sf.write("output.wav", result.audio, result.sample_rate)
+```
+
+Without `ref_audio`, the model synthesizes with a default voice.
+
+## Supported languages
+
+Cantonese, Chinese, Dutch, English, French, German, Italian, Japanese, Korean,
+Polish, Spanish (per the upstream preview release).
+
+## License
+
+Apache-2.0, following the upstream model. The bundled codec weights are part of the
+upstream repository and carry the same license.

codec.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:540d01e161e079fcff67b4a1b78ad5a0158be5b829a494033f4881c563502a3a
+size 1349643293

config.json

@@ -0,0 +1,51 @@
+{
+  "architectures": [
+    "ArkttsModel"
+  ],
+  "attention_o_bias": false,
+  "attention_qk_norm": false,
+  "attention_qkv_bias": true,
+  "codebook_size": 4096,
+  "codec_filename": "codec.safetensors",
+  "codec_frame_size": 2048,
+  "codec_post_intermediate_size": 1216,
+  "codec_post_n_head": 16,
+  "codec_post_n_layer": 8,
+  "codec_post_n_local_heads": 8,
+  "codec_sample_rate": 44100,
+  "dim": 896,
+  "dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "fast_attention_o_bias": false,
+  "fast_attention_qk_norm": false,
+  "fast_attention_qkv_bias": false,
+  "fast_dim": 896,
+  "fast_head_dim": 64,
+  "fast_intermediate_size": 4864,
+  "fast_n_head": 14,
+  "fast_n_local_heads": 2,
+  "head_dim": 64,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_seq_len": 2048,
+  "model_type": "arktts",
+  "n_fast_layer": 4,
+  "n_head": 14,
+  "n_layer": 24,
+  "n_local_heads": 2,
+  "norm_eps": 1e-06,
+  "norm_fastlayer_input": true,
+  "num_codebooks": 10,
+  "pad_token_id": 151643,
+  "ras_temperature": 1.0,
+  "ras_top_p": 0.9,
+  "ras_window_size": 10,
+  "rope_base": 1000000,
+  "semantic_begin_id": 151678,
+  "semantic_end_id": 155773,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.5",
+  "use_gradient_checkpointing": false,
+  "vocab_size": 155776
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "do_sample": true,
+  "eos_token_id": 151645,
+  "max_new_tokens": 512,
+  "pad_token_id": 151643,
+  "temperature": 0.7,
+  "top_k": 50,
+  "top_p": 0.9,
+  "transformers_version": "4.57.5"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2cc2dd288b71a5a476232f30531e0f011a32f27b7b81cdda727c102593f4020
+size 1202343821

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f24e08099d45a8adf3f52f5f0b03276e433bb9d689bb15fcbcc48ce58744588b
+size 12217872