Merge branch 'main' into dev

Author: 刘鑫

.gitignore

@@ -0,0 +1,3 @@
+launch.json
+__pycache__
+voxcpm.egg-info

README.md

@@ -62,10 +62,12 @@ By default, when you first run the script, the model will be downloaded automati
 ### 2. Basic Usage
 ```python
 import soundfile as sf
+import numpy as np
 from voxcpm import VoxCPM
 
 model = VoxCPM.from_pretrained("openbmb/VoxCPM-0.5B")
 
+# Non-streaming
 wav = model.generate(
     text="VoxCPM is an innovative end-to-end TTS model from ModelBest, designed to generate highly expressive speech.",
     prompt_wav_path=None,      # optional: path to a prompt speech for voice cloning
@@ -81,6 +83,18 @@ wav = model.generate(
 
 sf.write("output.wav", wav, 16000)
 print("saved: output.wav")
+
+# Streaming
+chunks = []
+for chunk in model.generate_streaming(
+    text = "Streaming text to speech is easy with VoxCPM!",
+    # supports same args as above
+):
+    chunks.append(chunk)
+wav = np.concatenate(chunks)
+
+sf.write("output_streaming.wav", wav, 16000)
+print("saved: output_streaming.wav")
 ```
 
 ### 3. CLI Usage

pyproject.toml

@@ -20,12 +20,10 @@ classifiers = [
     "Intended Audience :: Developers",
     "Operating System :: OS Independent",
     "Programming Language :: Python :: 3",
-    "Programming Language :: Python :: 3.8",
-    "Programming Language :: Python :: 3.9",
     "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
 ]
-requires-python = ">=3.8"
+requires-python = ">=3.10"
 dependencies = [
     "torch>=2.5.0",
     "torchaudio>=2.5.0",
@@ -78,7 +76,7 @@ version_scheme = "post-release"
 
 [tool.black]
 line-length = 120
-target-version = ['py38']
+target-version = ['py310']
 include = '\.pyi?$'
 extend-exclude = '''
 /(

src/voxcpm/core.py

@@ -1,8 +1,8 @@
-import torch
-import torchaudio
 import os
 import re
 import tempfile
+import numpy as np
+from typing import Generator
 from huggingface_hub import snapshot_download
 from .model.voxcpm import VoxCPMModel
 
@@ -11,6 +11,7 @@ def __init__(self,
             voxcpm_model_path : str,
             zipenhancer_model_path : str = "iic/speech_zipenhancer_ans_multiloss_16k_base",
             enable_denoiser : bool = True,
+            optimize: bool = True,
         ):
         """Initialize VoxCPM TTS pipeline.
 
@@ -21,9 +22,10 @@ def __init__(self,
             zipenhancer_model_path: ModelScope acoustic noise suppression model
                 id or local path. If None, denoiser will not be initialized.
             enable_denoiser: Whether to initialize the denoiser pipeline.
+            optimize: Whether to optimize the model with torch.compile. True by default, but can be disabled for debugging.
         """
         print(f"voxcpm_model_path: {voxcpm_model_path}, zipenhancer_model_path: {zipenhancer_model_path}, enable_denoiser: {enable_denoiser}")
-        self.tts_model = VoxCPMModel.from_local(voxcpm_model_path)
+        self.tts_model = VoxCPMModel.from_local(voxcpm_model_path, optimize=optimize)
         self.text_normalizer = None
         if enable_denoiser and zipenhancer_model_path is not None:
             from .zipenhancer import ZipEnhancer
@@ -43,6 +45,7 @@ def from_pretrained(cls,
             zipenhancer_model_id: str = "iic/speech_zipenhancer_ans_multiloss_16k_base",
             cache_dir: str = None,
             local_files_only: bool = False,
+            **kwargs,
         ):
         """Instantiate ``VoxCPM`` from a Hugging Face Hub snapshot.
 
@@ -54,6 +57,8 @@ def from_pretrained(cls,
             cache_dir: Custom cache directory for the snapshot.
             local_files_only: If True, only use local files and do not attempt
                 to download.
+        Kwargs:
+            Additional keyword arguments passed to the ``VoxCPM`` constructor.
 
         Returns:
             VoxCPM: Initialized instance whose ``voxcpm_model_path`` points to
@@ -82,9 +87,16 @@ def from_pretrained(cls,
             voxcpm_model_path=local_path,
             zipenhancer_model_path=zipenhancer_model_id if load_denoiser else None,
             enable_denoiser=load_denoiser,
+            **kwargs,
         )
 
-    def generate(self, 
+    def generate(self, *args, **kwargs) -> np.ndarray:
+        return next(self._generate(*args, streaming=False, **kwargs))
+
+    def generate_streaming(self, *args, **kwargs) -> Generator[np.ndarray, None, None]:
+        return self._generate(*args, streaming=True, **kwargs)
+
+    def _generate(self, 
             text : str,
             prompt_wav_path : str = None,
             prompt_text : str = None,
@@ -96,7 +108,8 @@ def generate(self,
             retry_badcase : bool = True,
             retry_badcase_max_times : int = 3,
             retry_badcase_ratio_threshold : float = 6.0,
-        ):
+            streaming: bool = False,
+        ) -> Generator[np.ndarray, None, None]:
         """Synthesize speech for the given text and return a single waveform.
 
         This method optionally builds and reuses a prompt cache. If an external
@@ -118,8 +131,11 @@ def generate(self,
             retry_badcase: Whether to retry badcase.
             retry_badcase_max_times: Maximum number of times to retry badcase.
             retry_badcase_ratio_threshold: Threshold for audio-to-text ratio.
+            streaming: Whether to return a generator of audio chunks.
         Returns:
-            numpy.ndarray: 1D waveform array (float32) on CPU.
+            Generator of numpy.ndarray: 1D waveform array (float32) on CPU. 
+            Yields audio chunks for each generations step if ``streaming=True``,
+            otherwise yields a single array containing the final audio.
         """
         if not text.strip() or not isinstance(text, str):
             raise ValueError("target text must be a non-empty string")
@@ -155,7 +171,7 @@ def generate(self,
                     self.text_normalizer = TextNormalizer()
                 text = self.text_normalizer.normalize(text)
 
-            wav, target_text_token, generated_audio_feat = self.tts_model.generate_with_prompt_cache(
+            generate_result = self.tts_model._generate_with_prompt_cache(
                             target_text=text,
                             prompt_cache=fixed_prompt_cache,
                             min_len=2,
@@ -165,9 +181,11 @@ def generate(self,
                             retry_badcase=retry_badcase,
                             retry_badcase_max_times=retry_badcase_max_times,
                             retry_badcase_ratio_threshold=retry_badcase_ratio_threshold,
+                            streaming=streaming,
                         )
 
-            return wav.squeeze(0).cpu().numpy()
+            for wav, _, _ in generate_result:
+                yield wav.squeeze(0).cpu().numpy()
 
         finally:
             if temp_prompt_wav_path and os.path.exists(temp_prompt_wav_path):