Add files using upload-large-folder tool

.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 +1,47 @@
+---
+license: apache-2.0
+base_model: Audio8/Audio8-TTS-Preview-0.6b
+pipeline_tag: text-to-speech
+language: [yue, zh, en, ja, ko, fr, de, es, it, nl, pl]
+tags: [mlx, apple-silicon, tts, bf16, voice-cloning, streaming, arktts]
+library_name: mlx
+---
+
+# Audio8-TTS-MLX-BF16
+
+Native MLX BF16 baseline of
+[Audio8/Audio8-TTS-Preview-0.6b](https://huggingface.co/Audio8/Audio8-TTS-Preview-0.6b)
+for Apple Silicon.
+
+Inference code, installation, API documentation, tests, and benchmark evidence:
+[vanch007/mlx-audio8-tts](https://github.com/vanch007/mlx-audio8-tts).
+
+## Artifact
+
+- 1,147 MiB language-model weights; 2.39 GiB complete repository download.
+- Bundled 1.26 GiB, 44.1 kHz neural codec with 10 acoustic codebooks.
+- Baseline for comparing the recommended
+  [8-bit release](https://huggingface.co/vanch007/Audio8-TTS-MLX-8bit).
+
+## M3 Max benchmark
+
+Measured RTF across the 11-language real-device matrix: 1.245–1.484. The
+matrix also covers zero-shot voice cloning and streaming. See the
+[evaluation report](https://github.com/vanch007/mlx-audio8-tts/tree/main/reports/evaluation).
+
+## Usage
+
+```bash
+git clone https://github.com/vanch007/mlx-audio8-tts.git
+cd mlx-audio8-tts
+pip install -e '.[server]'
+
+mlx-audio8-tts generate \
+  --model vanch007/Audio8-TTS-MLX-BF16 \
+  --text "Hello from the MLX BF16 baseline." \
+  --output output.wav
+```
+
+This is an independent Apache-2.0 MLX conversion. See the
+[upstream project](https://github.com/Audio8-AI/Audio8_TTS) for the original
+architecture and checkpoint.

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