lashman/whisper_voice
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 6 Wiki Activity

Release v1.0.4: The Compatibility Update

Browse Source 
- Added robust CPU Fallback for AMD/Non-CUDA GPUs.
- Implemented Lazy Load for AI Engine to prevent startup crashes.
- Added explicit DLL injection for Cublas/Cudnn on Windows.
- Added Corrupt Model Auto-Repair logic.
- Includes pre-compiled v1.0.4 executable.
This commit is contained in:
Your Name
2026-01-25 20:28:01 +02:00
parent aed489dd23
commit 6737ed4547
6 changed files with 125 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
README.md
View File

@@ -43,6 +43,18 @@ Whisper Voice operates directly on the metal. It is not an API wrapper; it is an
| **Sensory Gate** | **Silero VAD** | Enterprise-grade Voice Activity Detection filters out the noise, ensuring only pure intent is processed. |
| **Interface** | **Qt 6 / QML** | Hardware-accelerated, glassmorphic UI that is fluid, responsive, and sovereign. |
### 🛑 Compatibility Matrix (Windows)
The core engine (`CTranslate2`) is heavily optimized for Nvidia tensor cores.
| Manufacturer | Hardware | Status | Notes |
| :--- | :--- | :--- | :--- |
| **Nvidia** | GTX 900+ / RTX | ✅ **Supported** | Full heavy-metal acceleration. |
| **AMD** | Radeon RX | ⚠️ **CPU Fallback** | Runs on CPU. Valid for `Small/Medium`, slow for `Large`. |
| **Intel** | Arc / Iris | ⚠️ **CPU Fallback** | Runs on CPU. Valid for `Small/Medium`, slow for `Large`. |
| **Apple** | M1 / M2 / M3 | ❌ **Unsupported** | Release is strictly Windows x64. |
> **AMD Users**: v1.0.3 auto-detects GPU failures and silently falls back to CPU.
<br>
## 🖋️ Universal Transcription

40
RELEASE_NOTES.md
View File

@@ -1,28 +1,28 @@
# Release v1.0.2
# Release v1.0.4
**"The Lightweight Release"**
**"The Compatibility Update"**
This release focuses on removing bloat and switching to a native approach for punctuation, resulting in a significantly faster and smaller application.
This release focuses on maximum stability across different hardware configurations (AMD, Intel, Nvidia) and fixing startup crashes related to corrupted models or missing drivers.
## 🚀 Key Changes
## 🛠️ Critical Fixes
### 1. Style Prompting (Replaces Grammar Model)
We have removed the heavy "Grammar Correction" model (M2M100) and replaced it with **Style Prompting**.
* **How it works**: Uses Whisper's internal context awareness to force proper punctuation.
* **New Settings**: Go to `Settings -> AI Engine` to choose a style:
* **Standard**: (Default) Forces full sentences and proper punctuation.
* **Casual**: Relaxed, lowercase style.
* **Custom**: Enter your own prompt context.
### 1. Robust CPU Fallback (AMD / Intel Support)
* **Problem**: Previously, if an AMD user tried to run the app, it would crash instantly because it tried to load Nvidia CUDA libraries by default.
* **Fix**: The app now **silently detects** if CUDA initialization fails (due to missing DLLs or incompatible hardware) and **automatically falls back to CPU mode**.
* **Result**: The app "just works" on any Windows machine, regardless of GPU.
### 2. Bloat Removal
* **Removed**: `transformers`, `sentencepiece`, `accelerate` libraries.
* **Removed**: `grammar-m2m100` model downloader and logic.
* **Impact**: The application is lighter, installs faster, and uses less RAM.
### 2. Startup Crash Protection
* **Problem**: If `faster_whisper` was imported before checking for valid drivers, the app would crash on launch for some users.
* **Fix**: Implemented **Lazy Loading** for the AI engine. The app now starts the UI first, and only loads the heavy AI libraries inside a safety block that catches errors.
### 3. Stability Fixes
* **Fixed**: `NameError: 'torch' is not defined` when using Low VRAM Mode.
* **Fixed**: Bootstrapper now self-repairs missing dependencies if the environment gets corrupted.
### 3. Corrupt Model Auto-Repair
* **Problem**: Interrupted downloads could leave a corrupted model folder, preventing the app from ever starting again.
* **Fix**: If the app detects a "vocabulary missing" or invalid config error, it will now **automatically delete the corrupt folder** and allow you to re-download it cleanly.
### 4. Windows DLL Injection
* **Fix**: Added explicit DLL path injection for `nvidia-cublas` and `nvidia-cudnn` to ensure Python 3.8+ can find the required CUDA libraries on Windows systems that don't have them in PATH.
## 📦 Installation
1. Download `WhisperVoice.exe` (attached below or in `dist/`).
2. Run it. It will automatically update your environment if needed.
1. Download `WhisperVoice.exe` below.
2. Replace your existing `.exe`.
3. Run it.

BIN
dist/WhisperVoice.exe vendored
View File

Binary file not shown.

25
main.py
View File

@@ -9,6 +9,31 @@ app_dir = os.path.dirname(os.path.abspath(__file__))
if app_dir not in sys.path:
sys.path.insert(0, app_dir)
# -----------------------------------------------------------------------------
# WINDOWS DLL FIX (CRITICAL for Portable CUDA)
# Python 3.8+ on Windows requires explicit DLL directory addition.
# -----------------------------------------------------------------------------
if os.name == 'nt' and hasattr(os, 'add_dll_directory'):
try:
from pathlib import Path
# Scan sys.path for site-packages
for p in sys.path:
path_obj = Path(p)
if path_obj.name == 'site-packages' and path_obj.exists():
nvidia_path = path_obj / "nvidia"
if nvidia_path.exists():
for subdir in nvidia_path.iterdir():
# Add 'bin' folder from each nvidia stub (cublas, cudnn, etc.)
bin_path = subdir / "bin"
if bin_path.exists():
os.add_dll_directory(str(bin_path))
# Also try adding site-packages itself just in case
# os.add_dll_directory(str(path_obj))
break
except Exception:
pass
# -----------------------------------------------------------------------------
from PySide6.QtWidgets import QApplication, QFileDialog, QMessageBox
from PySide6.QtCore import QObject, Slot, Signal, QThread, Qt, QUrl
from PySide6.QtQml import QQmlApplicationEngine

70
src/core/transcriber.py
View File

@@ -21,7 +21,7 @@ except ImportError:
torch = None
# Import directly - valid since we are now running in the full environment
from faster_whisper import WhisperModel
class WhisperTranscriber:
"""
@@ -62,13 +62,32 @@ class WhisperTranscriber:
# Force offline if path exists to avoid HF errors
local_only = new_path.exists()
self.model = WhisperModel(
model_input,
device=device,
compute_type=compute,
download_root=str(get_models_path()),
local_files_only=local_only
)
try:
from faster_whisper import WhisperModel
self.model = WhisperModel(
model_input,
device=device,
compute_type=compute,
download_root=str(get_models_path()),
local_files_only=local_only
)
except Exception as load_err:
# CRITICAL FALLBACK: If CUDA/cublas fails (AMD/Intel users), fallback to CPU
err_str = str(load_err).lower()
if "cublas" in err_str or "cudnn" in err_str or "library" in err_str or "device" in err_str:
logging.warning(f"CUDA Init Failed ({load_err}). Falling back to CPU...")
self.config.set("compute_device", "cpu") # Update config for persistence/UI
self.current_compute_device = "cpu"
self.model = WhisperModel(
model_input,
device="cpu",
compute_type="int8", # CPU usually handles int8 well with newer extensions, or standard
download_root=str(get_models_path()),
local_files_only=local_only
)
else:
raise load_err
self.current_model_size = size
self.current_compute_device = device
@@ -78,6 +97,32 @@ class WhisperTranscriber:
except Exception as e:
logging.error(f"Failed to load model: {e}")
self.model = None
# Auto-Repair: Detect vocabulary/corrupt errors
err_str = str(e).lower()
if "vocabulary" in err_str or "tokenizer" in err_str or "config.json" in err_str:
# ... existing auto-repair logic ...
logging.warning("Corrupt model detected on load. Attempting to delete and reset...")
try:
import shutil
# Differentiate between simple path and HF path
new_path = get_models_path() / f"faster-whisper-{size}"
if new_path.exists():
shutil.rmtree(new_path)
logging.info(f"Deleted corrupt model at {new_path}")
else:
# Try legacy HF path
hf_path = get_models_path() / f"models--Systran--faster-whisper-{size}"
if hf_path.exists():
shutil.rmtree(hf_path)
logging.info(f"Deleted corrupt HF model at {hf_path}")
# Notify UI to refresh state (will show 'Download' button now)
# We can't reach bridge easily here without passing it in,
# but the UI polls or listens to logs.
# The user will simply see "Model Missing" in settings after this.
except Exception as del_err:
logging.error(f"Failed to delete corrupt model: {del_err}")
def transcribe(self, audio_data, is_file: bool = False, task: Optional[str] = None) -> str:
"""
@@ -89,7 +134,7 @@ class WhisperTranscriber:
if not self.model:
self.load_model()
if not self.model:
return "Error: Model failed to load."
return "Error: Model failed to load. Please check Settings -> Model Info."
try:
# Config
@@ -174,8 +219,11 @@ class WhisperTranscriber:
def model_exists(self, size: str) -> bool:
"""Checks if a model size is already downloaded."""
new_path = get_models_path() / f"faster-whisper-{size}"
if (new_path / "config.json").exists():
return True
if new_path.exists():
# Strict check
required = ["config.json", "model.bin", "vocabulary.json"]
if all((new_path / f).exists() for f in required):
return True
# Legacy HF cache check
folder_name = f"models--Systran--faster-whisper-{size}"

19
src/ui/bridge.py
View File

@@ -381,25 +381,24 @@ class UIBridge(QObject):
# Check new simple format used by DownloadWorker
path_simple = get_models_path() / f"faster-whisper-{size}"
if path_simple.exists() and any(path_simple.iterdir()):
return True
if path_simple.exists():
# Strict check: Ensure all critical files exist
required = ["config.json", "model.bin", "vocabulary.json"]
if all((path_simple / f).exists() for f in required):
return True
# Check HF Cache format (legacy/default)
folder_name = f"models--Systran--faster-whisper-{size}"
path_hf = get_models_path() / folder_name
snapshots = path_hf / "snapshots"
if snapshots.exists() and any(snapshots.iterdir()):
return True
# Check direct folder (simple)
path_direct = get_models_path() / size
if (path_direct / "config.json").exists():
return True
return True # Legacy cache structure is complex, assume valid if present
return False
except Exception as e:
logging.error(f"Error checking model status: {e}")
return False
return False
@Slot(str)
def downloadModel(self, size):