cutted 0.2.0__py3-none-any.whl → 0.3.1__py3-none-any.whl

cutted/__init__.py

@@ -1,2 +1,2 @@
-__version__ = "0.1.0"
+__version__ = "0.3.1"
 __author__ = "simon0302010"

cutted/app.py

@@ -8,14 +8,25 @@ from matplotlib.backends.backend_tkagg import FigureCanvasTkAgg
 
 customtkinter.set_appearance_mode("Dark")
 
+try:
+    from .core import transcribe
+    whisper_support = True
+    print_info("Whisper support present.")
+except:
+    whisper_support = False
+    print_info("Whisper support is not present.")
+
 class CuttedApp:
     def __init__(self):
         self.AudioProcessor = audio_processor.AudioProcessor()
+        if whisper_support:
+            self.whisper = None
         self.gemini = gemini.GeminiClient()
         self.canvas = None
         self.cursor_line = None
         self.last_slider_update = 0
         self.is_playing = False
+        self.last_states = []
         self.setup_ui()
     
     def setup_ui(self):
@@ -40,12 +51,24 @@ class CuttedApp:
         
         export_button = customtkinter.CTkButton(self.root, text="Export", command=self.export_audio, width=70)
         export_button.place(relx=0.9, rely=1.0, anchor="s", y=-30)
+        
+        undo_button = customtkinter.CTkButton(self.root, text="Undo", command=self.undo_last, width=70)
+        undo_button.place(relx=0.1, rely=1.0, anchor="s", y=-30)
+        
+        if whisper_support:
+            self.use_transcript_checkbox = customtkinter.CTkCheckBox(
+                self.root,
+                text="Give Gemini a transcript (very slow)",
+                text_color="#888888",
+                font=("Arial", 12)
+            )
+            self.use_transcript_checkbox.place(relx=0.0, rely=1.0, anchor="w", y=-12)
 
         self.play_button = customtkinter.CTkButton(self.root, text="Play", command=self.play_audio, width=50)
         self.play_button.place(relx=0.3, rely=1.0, anchor="s", y=-30)
         self.stop_button = customtkinter.CTkButton(self.root, text="Stop", command=self.stop_audio, width=50)
         self.stop_button.place(relx=0.7, rely=1.0, anchor="s", y=-30)
-
+        
         self.input_frame = customtkinter.CTkFrame(self.root, fg_color="transparent", height=36)
         self.input_frame.place(relx=0.5, rely=1.0, anchor="s", y=-90, relwidth=0.8)
 
@@ -153,12 +176,21 @@ class CuttedApp:
             print_success(f"Audio exported to {save_path}")
             
     def send_prompt(self):
+        self.save_state()
+
         if not hasattr(self.AudioProcessor, "audio") or self.AudioProcessor.audio is None:
             print_fail("No audio loaded.")
             return
         
         text = self.entry.get()
         full_prompt = f"You are a audio editing AI. You are controllable via natural language and editing a audio file. The audio file is {round(self.AudioProcessor.get_lenght())}s long."
+        if whisper_support:
+            if self.use_transcript_checkbox.get():
+                if not self.whisper:
+                    messagebox.showinfo("Info", "Loading Whisper model. This may take a few minutes depending on your internet connection. See the progress in your command line. If this window appears to be frozen, the transcription is running.")
+                    self.whisper = transcribe.Whisper()
+                transcript = self.whisper.transcribe(self.AudioProcessor.audio_path)
+                full_prompt += f"\nThis is a transcript with per word timestamps of the audio:\n{transcript}"
         full_prompt += f"\n\nUser Prompt: {text}"
         self.entry.delete(0, "end")
         
@@ -178,9 +210,25 @@ class CuttedApp:
         else:
             print_fail("Gemini returned no data")
 
+    def save_state(self):
+        if hasattr(self.AudioProcessor, "audio") and self.AudioProcessor.audio is not None:
+            self.last_states.append(self.AudioProcessor.audio._spawn(self.AudioProcessor.audio.raw_data))
+            if len(self.last_states) > 10:
+                self.last_states.pop(0) 
+           
+    def undo_last(self):
+        if len(self.last_states) == 0:
+            print_warn("No previous states to undo")
+            messagebox.showwarning("Warning", "No previous states to undo")
+            return
+        
+        self.AudioProcessor.audio = self.last_states.pop()
+        self.update_plot()
+        print_info("Undid last action")
+
     def run(self):
         self.root.mainloop()
         
 def main():
     app = CuttedApp()
-    app.run()
+    app.run()

cutted/core/transcribe.py

@@ -2,7 +2,7 @@ import json
 import whisper_timestamped as whisper
 
 class Whisper:
-    def __init__(self, model_size: str = "small", device: str = "cpu"):
+    def __init__(self, model_size: str = "small", device = None):
         self.model = whisper.load_model(
             model_size, device=device
         )

{cutted-0.2.0.dist-info → cutted-0.3.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cutted
-Version: 0.2.0
+Version: 0.3.1
 Summary: AI-powered audio editor controllable via natural language.
 Author-email: simon0302010 <simon0302010@gmail.com>
 License-Expression: GPL-3.0
@@ -15,6 +15,8 @@ Requires-Dist: pydub
 Requires-Dist: pygame
 Requires-Dist: google-genai
 Requires-Dist: python-dotenv
+Provides-Extra: whisper
+Requires-Dist: whisper-timestamped; extra == "whisper"
 Dynamic: license-file
 
 # Cutted

cutted-0.3.1.dist-info/RECORD

@@ -0,0 +1,12 @@
+cutted/__init__.py,sha256=Q7ZgbkmUOc-Gzy42zzZcKnzKxdZ023pITyXAC0BDBlM,49
+cutted/__main__.py,sha256=lYGLgtIZ_vGZIJmWG6ZQoqOdyOJnaWEA4NBn5Rc7Q8E,61
+cutted/app.py,sha256=xf5LFHdPLz1WNP05eRruHX2hKnaei8CUrqzVSODweAM,8952
+cutted/core/audio_processor.py,sha256=7-XCuPPTlozeuaD2LqyzwRGinu0NvowTLbAh2X4XJ98,5182
+cutted/core/gemini.py,sha256=Ts_EbC1-rO9jIsdSlzKcmjLVS1o663GmfTdzmix12kE,2872
+cutted/core/logger.py,sha256=AjqrgW2LV9HdPkPQ8oOmyd9lWzVSIg46r74ILR7mVHo,585
+cutted/core/transcribe.py,sha256=0e7aCva4y6D-gKe1xw5HT9VoFgbvHGgV6utn12r8wXA,986
+cutted-0.3.1.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+cutted-0.3.1.dist-info/METADATA,sha256=6plv-IaqUXQeeAnChYaMBjYSLh8FBTAtvyQqZkRTuuA,1201
+cutted-0.3.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+cutted-0.3.1.dist-info/top_level.txt,sha256=PL6glZvzRyKWCDn5aoYI9uH8HlEA5Qd_XFJowJKARYI,7
+cutted-0.3.1.dist-info/RECORD,,

cutted-0.2.0.dist-info/RECORD

@@ -1,12 +0,0 @@
-cutted/__init__.py,sha256=CP0x3JIScNbFVSOoF3eIQTKD5gDRfWXcCFE46rlZCio,49
-cutted/__main__.py,sha256=lYGLgtIZ_vGZIJmWG6ZQoqOdyOJnaWEA4NBn5Rc7Q8E,61
-cutted/app.py,sha256=qZ6idEqEmdtCLOahBN4803u-t12oNRhTAgbN3XiIiKY,6803
-cutted/core/audio_processor.py,sha256=7-XCuPPTlozeuaD2LqyzwRGinu0NvowTLbAh2X4XJ98,5182
-cutted/core/gemini.py,sha256=Ts_EbC1-rO9jIsdSlzKcmjLVS1o663GmfTdzmix12kE,2872
-cutted/core/logger.py,sha256=AjqrgW2LV9HdPkPQ8oOmyd9lWzVSIg46r74ILR7mVHo,585
-cutted/core/transcribe.py,sha256=cm6ziM3_grXKpUCFHiAU7-6lFK_SVsf7-6n14vMYQng,992
-cutted-0.2.0.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-cutted-0.2.0.dist-info/METADATA,sha256=4hl_l2XcGg74HKYMcbAlklxduA8nw066deSAVBBuvOs,1122
-cutted-0.2.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-cutted-0.2.0.dist-info/top_level.txt,sha256=PL6glZvzRyKWCDn5aoYI9uH8HlEA5Qd_XFJowJKARYI,7
-cutted-0.2.0.dist-info/RECORD,,