Upload folder using huggingface_hub

.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 +1,63 @@
+---
+library_name: mlx-audio-plus
+base_model:
+- ASLP-lab/WSYue-TTS
+tags:
+- mlx
+- tts
+- cosyvoice2
+pipeline_tag: text-to-speech
+language:
+- en
+- zh
+- ja
+- ko
+---
+
+# jackuh02/CosyVoice2-Yue-mlx
+
+This model was converted to MLX format from [ASLP-lab/WSYue-TTS/CosyVoice2-Yue](https://huggingface.co/ASLP-lab/WSYue-TTS) using [mlx-audio-plus](https://github.com/DePasqualeOrg/mlx-audio-plus) version **0.1.8**.
+
+## Usage
+
+```bash
+pip install -U mlx-audio-plus
+```
+
+### Inference Modes
+
+| Mode | Parameters | Description |
+|------|------------|-------------|
+| Cross-lingual | `ref_audio` | Zero-shot TTS (default) |
+| Zero-shot | `ref_audio` + `ref_text` | Better quality with transcription |
+| Instruct | `ref_audio` + `instruct_text` | Style control (e.g., "speak slowly") |
+| Voice Conversion | `source_audio` + `ref_audio` | Convert audio to target voice |
+
+### Command line
+
+```bash
+# Cross-lingual (default)
+mlx_audio.tts --model jackuh02/CosyVoice2-Yue-mlx --text "Hello!" --ref_audio ref.wav
+
+# Zero-shot (with transcription)
+mlx_audio.tts --model jackuh02/CosyVoice2-Yue-mlx --text "Hello!" --ref_audio ref.wav --ref_text "Transcription of ref audio."
+
+# Instruct (style control)
+mlx_audio.tts --model jackuh02/CosyVoice2-Yue-mlx --text "Hello!" --ref_audio ref.wav --instruct_text "Speak slowly and calmly"
+
+# Voice Conversion
+mlx_audio.tts --model jackuh02/CosyVoice2-Yue-mlx --source_audio source.wav --ref_audio ref.wav
+```
+
+### Python
+
+```python
+from mlx_audio.tts.generate import generate_audio
+
+generate_audio(
+    text="Hello, this is CosyVoice2 on MLX!",
+    model="jackuh02/CosyVoice2-Yue-mlx",
+    ref_audio="reference.wav",
+    file_prefix="output",
+)
+```

config.json

@@ -0,0 +1,8 @@
+{
+  "model_type": "cosyvoice2",
+  "version": "0.5B",
+  "sample_rate": 24000,
+  "mel_channels": 80,
+  "speech_token_size": 6561,
+  "dtype": "float16"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e55b118a99b5f665b43a63db900741f6856f1f82522516ed52e1a82e9ce6b964
+size 1564752978

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e3855f008ece7e02f09bad5c0aa492cd1594529a796b80193f4ef640200e58b
+size 10523354

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}