Upload folder using huggingface_hub

README.md

@@ -0,0 +1,45 @@
+---
+library_name: mlx-audio-plus
+base_model:
+- ResembleAI/chatterbox-turbo
+tags:
+- mlx
+- tts
+- chatterbox
+pipeline_tag: text-to-speech
+language:
+- en
+---
+
+# Chatterbox-Turbo-TTS-4bit
+
+This model was converted to MLX format from [ResembleAI/chatterbox-turbo](https://huggingface.co/ResembleAI/chatterbox-turbo) using [mlx-audio-plus](https://github.com/DePasqualeOrg/mlx-audio-plus) version **0.1.6**.
+
+This model uses **4-bit quantization** for the T3 GPT2 backbone, reducing memory usage while maintaining audio quality.
+
+**Note:** This model requires the S3Tokenizer weights from [mlx-community/S3TokenizerV2](https://huggingface.co/mlx-community/S3TokenizerV2), which will be downloaded automatically.
+
+## Use with mlx-audio-plus
+
+```bash
+pip install -U mlx-audio-plus
+```
+
+### Command line
+
+```bash
+mlx_audio.tts --model /path/to/Chatterbox-Turbo-TTS-4bit --text "Hello, this is Chatterbox Turbo on MLX!" --ref_audio reference.wav
+```
+
+### Python
+
+```python
+from mlx_audio.tts.generate import generate_audio
+
+generate_audio(
+    text="Hello, this is Chatterbox Turbo on MLX!",
+    model="/path/to/Chatterbox-Turbo-TTS-4bit",
+    ref_audio="reference.wav",
+    file_prefix="output",
+)
+```

conds.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4304e325697569fc0fa064925196edd2aa9a1d4da93f8a3cca042343abce0206
+size 167380

config.json

@@ -0,0 +1,12 @@
+{
+  "model_type": "chatterbox_turbo",
+  "version": "1.0",
+  "dtype": "float16",
+  "quantization": {
+    "bits": 4,
+    "group_size": 64,
+    "quantized_components": [
+      "t3.tfmr.h"
+    ]
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:864459cf462c833c4049d16302f721ceba5e24b66a4898af71bb769d5b5a2eab
+size 811560910

tokenizer_config.json

@@ -0,0 +1,175 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "[angry]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "[fear]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "[surprised]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "[whispering]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "[advertisement]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "[dramatic]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "[narration]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "[crying]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "[happy]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "[sarcastic]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "[clear throat]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "[sigh]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "[shush]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "[cough]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "[groan]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "[sniff]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "[gasp]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "[chuckle]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "[laugh]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}