Mirror from mlx-community/S3TokenizerV2

README.md

@@ -0,0 +1,14 @@
+---
+library_name: mlx-audio-plus
+base_model:
+- FunAudioLLM/CosyVoice2-0.5B
+tags:
+- mlx
+- speech-tokenizer
+---
+
+# mlx-community/S3TokenizerV2
+
+S3TokenizerV2 (Supervised Semantic Speech Tokenizer) converted to MLX format from [FunAudioLLM/CosyVoice2-0.5B](https://huggingface.co/FunAudioLLM/CosyVoice2-0.5B).
+
+This tokenizer is automatically downloaded when using Chatterbox or CosyVoice2 with [mlx-audio-plus](https://github.com/DePasqualeOrg/mlx-audio-plus).

config.json

@@ -0,0 +1,7 @@
+{
+  "model_type": "s3_tokenizer_v2",
+  "version": "2.0",
+  "sample_rate": 16000,
+  "token_rate": 25,
+  "codebook_size": 6561
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:928726bc1f206a613d36b8f49e297eae9c5593a21bf9b92ddfe2c23f85eb92cc
+size 494868984