tour/verbatim-dicta
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

init

Browse Source
This commit is contained in:
mike
2025-12-17 22:11:08 +01:00
parent 36852dde18
commit a53c0e2902
8 changed files with 218 additions and 239 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
transcribe_speakers.py
View File

@@ -79,17 +79,28 @@ class WindowsLoopbackAudioCapture:
dev['max_input_channels'] > 0):
return dev
# Auto-detect: look for WASAPI speakers/headphones
# Auto-detect: look for WASAPI speakers/headphones (Windows)
for dev in devices:
if (dev['max_input_channels'] > 0 and
any(x in dev['name'] for x in ['Speakers', 'Headphones', 'Output'])):
return dev
# Fallback: Stereo Mix or similar
# Fallback: Stereo Mix or similar (Windows)
for dev in devices:
if 'Stereo Mix' in dev['name']:
return dev
# Linux fallback: use default input device (pipewire/pulse)
try:
default_input_idx = sd.default.device[0] # Default input device
if default_input_idx is not None:
dev = devices[default_input_idx]
if dev['max_input_channels'] > 0:
print("⚠️ Note: Using default input device (microphone). For speaker capture on Linux, use transcribe_dual_linux.py")
return dev
except:
pass
return None
def _audio_callback(self, indata, frames, time_info, status):
@@ -511,8 +522,8 @@ Examples:
help="GPU device index to use (default: 0)")
parser.add_argument("--enable-llm", action="store_true",
help="Enable LLM analysis (fact-checking and questions)")
parser.add_argument("--llm-model", default="gpt-oss:20b",
help="Ollama model to use for LLM analysis (default: gpt-oss:20b)")
parser.add_argument("--llm-model", default="llama3.2:latest",
help="Ollama model to use for LLM analysis (default: llama3.2:latest)")
parser.add_argument("--llm-debug", action="store_true",
help="Show LLM raw responses for debugging")
parser.add_argument("--sentence-mode", action="store_true",