Upload folder using huggingface_hub

audio_encoder.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f05113710920de3e02131aad3c0cc22ae93d8a3bf4dede2a0d0d90fd8ba67e6f
-size 2116922802
+oid sha256:3b5166e4db06a3d0ac0b2bc22f96ff93fe8b858f33b6908b8250936fbf5adbf4
+size 3206917674

tokenizer_config.json

@@ -193,6 +193,6 @@
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,
-  "tokenizer_class": "VibeVoiceASRTextTokenizer",
+  "tokenizer_class": "Qwen2TokenizerFast",
   "unk_token": null
 }

vibevoice_asr_tokenizer_export.json

@@ -1,8 +1,9 @@
 {
-  "source_model_path": "microsoft/VibeVoice-ASR",
+  "source_model_path": "/home/ritsuko/.cache/huggingface/hub/models--microsoft--VibeVoice-ASR/snapshots/d0c9efdb8d614685062c04425d91e01b6f37d944",
   "language_model_pretrained_name": "Qwen/Qwen2.5-7B",
   "tokenizer_source": "/home/ritsuko/.cache/huggingface/hub/models--Qwen--Qwen2.5-7B/snapshots/d149729398750b98c0af14eb82c78cfe92750796",
-  "tokenizer_class": "VibeVoiceASRTextTokenizerFast",
+  "tokenizer_class": "Qwen2TokenizerFast",
+  "created_with_tokenizer_class": "VibeVoiceASRTextTokenizerFast",
   "speech_token_ids": {
     "<|object_ref_start|>": 151646,
     "<|object_ref_end|>": 151647,