fix: Linux/Ubuntu support — icon fallback, HiDPI scaling, CUDA lib paths, per-file timing
- app.py: graceful icon loading (no crash on Linux Tk without .ico support) - app.py: auto-detect display scaling for 4K/HiDPI screens - _LocalTranscribe.py: register NVIDIA pip-package .so paths on Linux (LD_LIBRARY_PATH) so faster-whisper finds libcublas/libcudnn at runtime - _LocalTranscribe.py: auto-fallback to CPU if CUDA runtime libs missing - _LocalTranscribe.py: filter input to supported media extensions only - _LocalTranscribe.py: show real decode errors instead of generic skip message - _LocalTranscribe.py: per-file timer showing wall-clock vs audio duration
This commit is contained in:
soderstromkr
33
app.py
33
app.py
@@ -52,6 +52,34 @@ customtkinter.set_appearance_mode("System")
|
||||
customtkinter.set_default_color_theme("blue") # Themes: blue (default), dark-blue, green
|
||||
firstclick = True
|
||||
|
||||
|
||||
def _set_app_icon(root):
|
||||
"""Set app icon when supported, without crashing on unsupported platforms."""
|
||||
base_dir = os.path.dirname(os.path.abspath(__file__))
|
||||
icon_path = os.path.join(base_dir, "images", "icon.ico")
|
||||
|
||||
if not os.path.exists(icon_path):
|
||||
return
|
||||
|
||||
try:
|
||||
root.iconbitmap(icon_path)
|
||||
except tk.TclError:
|
||||
# Some Linux Tk builds don't accept .ico for iconbitmap.
|
||||
pass
|
||||
|
||||
|
||||
def _apply_display_scaling(root):
|
||||
"""Auto-scale UI for high-resolution displays (e.g., 4K)."""
|
||||
try:
|
||||
screen_w = root.winfo_screenwidth()
|
||||
screen_h = root.winfo_screenheight()
|
||||
scale = min(screen_w / 1920.0, screen_h / 1080.0)
|
||||
scale = max(1.0, min(scale, 2.0))
|
||||
customtkinter.set_widget_scaling(scale)
|
||||
customtkinter.set_window_scaling(scale)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
class App:
|
||||
def __init__(self, master):
|
||||
self.master = master
|
||||
@@ -184,13 +212,14 @@ class App:
|
||||
if __name__ == "__main__":
|
||||
# Setting custom themes
|
||||
root = customtkinter.CTk()
|
||||
_apply_display_scaling(root)
|
||||
root.title("Local Transcribe with Whisper")
|
||||
# Geometry — taller to accommodate the embedded console panel
|
||||
width, height = 550, 560
|
||||
root.geometry('{}x{}'.format(width, height))
|
||||
root.minsize(450, 480)
|
||||
# Icon
|
||||
root.iconbitmap('images/icon.ico')
|
||||
# Icon (best-effort; ignored on platforms/builds without .ico support)
|
||||
_set_app_icon(root)
|
||||
# Run
|
||||
app = App(root)
|
||||
root.mainloop()
|
||||
|
||||
@@ -1,46 +1,71 @@
|
||||
import os
|
||||
import sys
|
||||
import datetime
|
||||
import time
|
||||
import site
|
||||
from glob import glob
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# CUDA setup — must happen before importing faster_whisper / ctranslate2
|
||||
# ---------------------------------------------------------------------------
|
||||
def _setup_cuda_dlls():
|
||||
"""Add NVIDIA pip-package DLL dirs to the DLL search path (Windows only).
|
||||
def _setup_cuda_libs():
|
||||
"""Register NVIDIA pip-package lib dirs so ctranslate2 finds CUDA at runtime.
|
||||
|
||||
pip-installed nvidia-cublas-cu12 / nvidia-cudnn-cu12 place their .dll
|
||||
files inside the site-packages tree. Python 3.8+ on Windows does NOT
|
||||
search PATH for DLLs loaded via ctypes/LoadLibrary, so we must
|
||||
explicitly register every nvidia/*/bin and nvidia/*/lib directory using
|
||||
os.add_dll_directory *and* prepend them to PATH (some native extensions
|
||||
still rely on PATH).
|
||||
pip-installed nvidia-cublas-cu12 / nvidia-cudnn-cu12 place their shared
|
||||
libraries inside the site-packages tree. Neither Windows nor Linux
|
||||
automatically search those directories, so we must register them
|
||||
explicitly:
|
||||
- Windows: os.add_dll_directory() + PATH
|
||||
- Linux: LD_LIBRARY_PATH (read by the dynamic linker)
|
||||
"""
|
||||
if sys.platform != "win32":
|
||||
return
|
||||
try:
|
||||
for sp in site.getsitepackages():
|
||||
nvidia_root = os.path.join(sp, "nvidia")
|
||||
if not os.path.isdir(nvidia_root):
|
||||
continue
|
||||
for pkg in os.listdir(nvidia_root):
|
||||
for sub in ("bin", "lib"):
|
||||
d = os.path.join(nvidia_root, pkg, sub)
|
||||
if os.path.isdir(d):
|
||||
os.environ["PATH"] = d + os.pathsep + os.environ.get("PATH", "")
|
||||
try:
|
||||
os.add_dll_directory(d)
|
||||
except (OSError, AttributeError):
|
||||
pass
|
||||
except Exception:
|
||||
pass
|
||||
sp_dirs = site.getsitepackages()
|
||||
except AttributeError:
|
||||
# virtualenv without site-packages helper
|
||||
sp_dirs = [os.path.join(sys.prefix, "lib",
|
||||
"python" + ".".join(map(str, sys.version_info[:2])),
|
||||
"site-packages")]
|
||||
|
||||
_setup_cuda_dlls()
|
||||
for sp in sp_dirs:
|
||||
nvidia_root = os.path.join(sp, "nvidia")
|
||||
if not os.path.isdir(nvidia_root):
|
||||
continue
|
||||
for pkg in os.listdir(nvidia_root):
|
||||
for sub in ("bin", "lib"):
|
||||
d = os.path.join(nvidia_root, pkg, sub)
|
||||
if not os.path.isdir(d):
|
||||
continue
|
||||
if sys.platform == "win32":
|
||||
os.environ["PATH"] = d + os.pathsep + os.environ.get("PATH", "")
|
||||
try:
|
||||
os.add_dll_directory(d)
|
||||
except (OSError, AttributeError):
|
||||
pass
|
||||
else:
|
||||
# Linux / macOS — prepend to LD_LIBRARY_PATH
|
||||
ld = os.environ.get("LD_LIBRARY_PATH", "")
|
||||
if d not in ld:
|
||||
os.environ["LD_LIBRARY_PATH"] = d + (":" + ld if ld else "")
|
||||
# Also load via ctypes so already-started process sees it
|
||||
import ctypes
|
||||
try:
|
||||
for so in sorted(os.listdir(d)):
|
||||
if so.endswith(".so") or ".so." in so:
|
||||
ctypes.cdll.LoadLibrary(os.path.join(d, so))
|
||||
except OSError:
|
||||
pass
|
||||
|
||||
_setup_cuda_libs()
|
||||
|
||||
from faster_whisper import WhisperModel
|
||||
|
||||
|
||||
SUPPORTED_EXTENSIONS = {
|
||||
".wav", ".mp3", ".m4a", ".flac", ".ogg", ".wma", ".aac",
|
||||
".mp4", ".mkv", ".mov", ".webm", ".avi", ".mpeg", ".mpg",
|
||||
}
|
||||
|
||||
|
||||
def _detect_device():
|
||||
"""Return (device, compute_type) for the best available backend."""
|
||||
try:
|
||||
@@ -55,8 +80,15 @@ def _detect_device():
|
||||
|
||||
# Get the path
|
||||
def get_path(path):
|
||||
glob_file = glob(path + '/*')
|
||||
return glob_file
|
||||
all_items = glob(path + '/*')
|
||||
media_files = []
|
||||
for item in all_items:
|
||||
if not os.path.isfile(item):
|
||||
continue
|
||||
_, ext = os.path.splitext(item)
|
||||
if ext.lower() in SUPPORTED_EXTENSIONS:
|
||||
media_files.append(item)
|
||||
return sorted(media_files)
|
||||
|
||||
# Main function
|
||||
def transcribe(path, glob_file, model=None, language=None, verbose=False):
|
||||
@@ -95,15 +127,40 @@ def transcribe(path, glob_file, model=None, language=None, verbose=False):
|
||||
|
||||
# ── Step 2: Load model ───────────────────────────────────────────
|
||||
print(f"⏳ Loading model '{model}' — downloading if needed...")
|
||||
whisper_model = WhisperModel(model, device=device, compute_type=compute_type)
|
||||
try:
|
||||
whisper_model = WhisperModel(model, device=device, compute_type=compute_type)
|
||||
except Exception as exc:
|
||||
err = str(exc).lower()
|
||||
cuda_runtime_missing = (
|
||||
device == "cuda"
|
||||
and (
|
||||
"libcublas" in err
|
||||
or "libcudnn" in err
|
||||
or "cuda" in err
|
||||
or "cannot be loaded" in err
|
||||
or "not found" in err
|
||||
)
|
||||
)
|
||||
if not cuda_runtime_missing:
|
||||
raise
|
||||
print("⚠ CUDA runtime not available; falling back to CPU (int8).")
|
||||
print(f" Reason: {exc}")
|
||||
device, compute_type = "cpu", "int8"
|
||||
whisper_model = WhisperModel(model, device=device, compute_type=compute_type)
|
||||
print("✅ Model ready!")
|
||||
print(SEP)
|
||||
|
||||
# ── Step 3: Transcribe files ─────────────────────────────────────
|
||||
total_files = len(glob_file)
|
||||
print(f"📂 Found {total_files} item(s) in folder")
|
||||
print(f"📂 Found {total_files} supported media file(s) in folder")
|
||||
print(SEP)
|
||||
|
||||
if total_files == 0:
|
||||
output_text = '⚠ No supported media files found — try another folder.'
|
||||
print(output_text)
|
||||
print(SEP)
|
||||
return output_text
|
||||
|
||||
files_transcripted = []
|
||||
file_num = 0
|
||||
for file in glob_file:
|
||||
@@ -112,11 +169,13 @@ def transcribe(path, glob_file, model=None, language=None, verbose=False):
|
||||
print(f"\n{'─' * 46}")
|
||||
print(f"📄 File {file_num}/{total_files}: {title}")
|
||||
try:
|
||||
t_start = time.time()
|
||||
segments, info = whisper_model.transcribe(
|
||||
file,
|
||||
language=language,
|
||||
beam_size=5
|
||||
)
|
||||
audio_duration = info.duration # seconds
|
||||
# Make folder if missing
|
||||
os.makedirs('{}/transcriptions'.format(path), exist_ok=True)
|
||||
# Stream segments as they are decoded
|
||||
@@ -133,10 +192,16 @@ def transcribe(path, glob_file, model=None, language=None, verbose=False):
|
||||
else:
|
||||
print(" Transcribed up to %.0fs..." % seg.end, end='\r')
|
||||
segment_list.append(seg)
|
||||
elapsed = time.time() - t_start
|
||||
elapsed_min = elapsed / 60.0
|
||||
audio_min = audio_duration / 60.0
|
||||
ratio = audio_duration / elapsed if elapsed > 0 else float('inf')
|
||||
print(f"✅ Done — saved to transcriptions/{title}.txt")
|
||||
print(f"⏱ Transcribed {audio_min:.1f} min of audio in {elapsed_min:.1f} min ({ratio:.1f}x realtime)")
|
||||
files_transcripted.append(segment_list)
|
||||
except Exception:
|
||||
print('⚠ Not a valid audio/video file, skipping.')
|
||||
except Exception as exc:
|
||||
print(f"⚠ Could not decode '{os.path.basename(file)}', skipping.")
|
||||
print(f" Reason: {exc}")
|
||||
|
||||
# ── Summary ──────────────────────────────────────────────────────
|
||||
print(f"\n{SEP}")
|
||||
|
||||
Reference in New Issue
Block a user