modify imports

app.py

@@ -10,9 +10,9 @@ import threading
 from spaces import GPU
 from datetime import datetime
 
-from vibevoice.modular.modeling_vibevoice_inference import VibeVoiceForConditionalGenerationInference
-from vibevoice.processor.vibevoice_processor import VibeVoiceProcessor
-from vibevoice.modular.streamer import AudioStreamer
+from modular.modeling_vibevoice_inference import VibeVoiceForConditionalGenerationInference
+from processor.vibevoice_processor import VibeVoiceProcessor
+from modular.streamer import AudioStreamer
 from transformers.utils import logging
 from transformers import set_seed
 

modular/modeling_vibevoice.py

@@ -19,7 +19,7 @@ from transformers.utils import logging
 
 from .modular_vibevoice_tokenizer import VibeVoiceTokenizerStreamingCache, VibeVoiceAcousticTokenizerModel, VibeVoiceSemanticTokenizerModel
 from .modular_vibevoice_diffusion_head import VibeVoiceDiffusionHead
-from vibevoice.schedule.dpm_solver import DPMSolverMultistepScheduler
+from schedule.dpm_solver import DPMSolverMultistepScheduler
 
 from .configuration_vibevoice import VibeVoiceConfig
 

modular/modeling_vibevoice_inference.py

@@ -17,7 +17,7 @@ from transformers.utils import logging
 # from .modular_vibevoice_tokenizer import VibeVoiceTokenizerStreamingCache, VibeVoiceAcousticTokenizerModel, VibeVoiceSemanticTokenizerModel
 from .modular_vibevoice_tokenizer import VibeVoiceTokenizerStreamingCache, VibeVoiceTokenizerEncoderOutput
 from .modular_vibevoice_diffusion_head import VibeVoiceDiffusionHead
-from vibevoice.schedule.dpm_solver import DPMSolverMultistepScheduler
+from schedule.dpm_solver import DPMSolverMultistepScheduler
 
 from .configuration_vibevoice import VibeVoiceConfig
 

processor/vibevoice_processor.py

@@ -57,7 +57,7 @@ class VibeVoiceProcessor:
         import os
         import json
         from .vibevoice_tokenizer_processor import VibeVoiceTokenizerProcessor
-        from vibevoice.modular.modular_vibevoice_text_tokenizer import (
+        from modular.modular_vibevoice_text_tokenizer import (
             VibeVoiceTextTokenizer, 
             VibeVoiceTextTokenizerFast
         )

scripts/convert_nnscaler_checkpoint_to_transformers.py

@@ -9,10 +9,10 @@ import re
 import torch
 from typing import Dict, List, Tuple
 
-from vibevoice.modular.configuration_vibevoice import (
+from modular.configuration_vibevoice import (
     VibeVoiceConfig
 )
-from vibevoice.modular.modeling_vibevoice import VibeVoiceForConditionalGeneration
+from modular.modeling_vibevoice import VibeVoiceForConditionalGeneration
 from transformers.utils import logging
 
 logger = logging.get_logger(__name__)