gpu self hosted setup guide (no-mistakes)

This commit is contained in:
Igor Loskutov
2025-12-09 11:25:09 -05:00
parent 5779478d3c
commit 2b3f28993f
14 changed files with 799 additions and 26 deletions

View File

@@ -129,6 +129,11 @@ class WhisperService:
audio = np.frombuffer(proc.stdout, dtype=np.float32)
return audio
# IMPORTANT: This VAD segment logic is duplicated in multiple files for deployment isolation.
# If you modify this function, you MUST update all copies:
# - gpu/modal_deployments/reflector_transcriber.py
# - gpu/modal_deployments/reflector_transcriber_parakeet.py
# - gpu/self_hosted/app/services/transcriber.py (this file)
def vad_segments(
audio_array,
sample_rate: int = SAMPLE_RATE,
@@ -153,6 +158,10 @@ class WhisperService:
end = speech["end"]
yield (start / float(SAMPLE_RATE), end / float(SAMPLE_RATE))
start = None
# Handle case where audio ends while speech is still active
if start is not None:
audio_duration = len(audio_array) / float(sample_rate)
yield (start / float(SAMPLE_RATE), audio_duration)
iterator.reset_states()
audio_array = load_audio_via_ffmpeg(file_path, SAMPLE_RATE)

View File

@@ -34,6 +34,12 @@ def ensure_dirs():
UPLOADS_PATH.mkdir(parents=True, exist_ok=True)
# IMPORTANT: This function is duplicated in multiple files for deployment isolation.
# If you modify the audio format detection logic, you MUST update all copies:
# - gpu/self_hosted/app/utils.py (this file)
# - gpu/modal_deployments/reflector_transcriber.py (2 copies)
# - gpu/modal_deployments/reflector_transcriber_parakeet.py
# - gpu/modal_deployments/reflector_diarizer.py
def detect_audio_format(url: str, headers: Mapping[str, str]) -> str:
url_path = urlparse(url).path
for ext in SUPPORTED_FILE_EXTENSIONS:
@@ -47,6 +53,8 @@ def detect_audio_format(url: str, headers: Mapping[str, str]) -> str:
return "wav"
if "audio/mp4" in content_type:
return "mp4"
if "audio/webm" in content_type or "video/webm" in content_type:
return "webm"
raise HTTPException(
status_code=400,