LLM/WhisperLiveKit
1
0
Fork 0
mirror of https://github.com/QuentinFuxa/WhisperLiveKit.git synced 2026-03-07 14:23:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

speaker -1 are no more sent in websocket - no buffer when their is a silence

Browse Source
This commit is contained in:
Quentin Fuxa
2025-08-21 14:09:02 +02:00
parent d94a07d417
commit 909ac9dd41
3 changed files with 18 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
whisperlivekit/audio_processor.py
View File

@@ -301,7 +301,9 @@ class AudioProcessor:
transcription_lag_s = max(0.0, time() - self.beg_loop - self.end_buffer)
asr_processing_logs = f"internal_buffer={asr_internal_buffer_duration_s:.2f}s | lag={transcription_lag_s:.2f}s |"
if type(item) is Silence:
asr_processing_logs += f" + Silence of = {item.duration:.2f}s | last_end = {self.tokens[-1].end} |"
asr_processing_logs += f" + Silence of = {item.duration:.2f}s"
if self.tokens:
asr_processing_logs += " | last_end = {self.tokens[-1].end} |"
logger.info(asr_processing_logs)
if type(item) is Silence:
@@ -445,12 +447,15 @@ class AudioProcessor:
last_end_diarized = 0
undiarized_text = []
current_time = time() - self.beg_loop if self.beg_loop else None
tokens, buffer_transcription = handle_silences(tokens, buffer_transcription, current_time, self.silence)
tokens, buffer_transcription, buffer_diarization = handle_silences(tokens, buffer_transcription, buffer_diarization, current_time, self.silence)
for token in tokens:
speaker = token.speaker
if speaker == -1: #Speaker -1 means no attributed by diarization. In the frontend, it should appear under 'Speaker 1'
speaker = 1
# Handle diarization
if self.args.diarization:
if self.args.diarization and not tokens[-1].speaker == -2:
if (speaker in [-1, 0]) and token.end >= end_attributed_speaker:
undiarized_text.append(token.text)
continue

15
whisperlivekit/remove_silences.py
View File

@@ -77,9 +77,9 @@ def no_token_to_silence(tokens):
new_tokens.append(token)
return new_tokens
def ends_with_silence(tokens, buffer_transcription, current_time, vac_detected_silence):
def ends_with_silence(tokens, buffer_transcription, buffer_diarization, current_time, vac_detected_silence):
if not tokens:
return []
return [], buffer_transcription, buffer_diarization
last_token = tokens[-1]
if tokens and (
current_time - last_token.end >= END_SILENCE_DURATION
@@ -97,13 +97,14 @@ def ends_with_silence(tokens, buffer_transcription, current_time, vac_detected_s
probability=0.95
)
)
#We validate the buffer has because of the silence
return tokens
buffer_transcription = "" # for whisperstreaming backend, we should probably validate the buffer has because of the silence
buffer_diarization = ""
return tokens, buffer_transcription, buffer_diarization
def handle_silences(tokens, buffer_transcription, current_time, vac_detected_silence):
def handle_silences(tokens, buffer_transcription, buffer_diarization, current_time, vac_detected_silence):
tokens = blank_to_silence(tokens) #useful for simulstreaming backend which tends to generate [BLANK_AUDIO] text
tokens = no_token_to_silence(tokens)
tokens = ends_with_silence(tokens, buffer_transcription, current_time, vac_detected_silence)
return tokens, buffer_transcription
tokens, buffer_transcription, buffer_diarization = ends_with_silence(tokens, buffer_transcription, buffer_diarization, current_time, vac_detected_silence)
return tokens, buffer_transcription, buffer_diarization

6
whisperlivekit/web/live_transcription.js
View File

@@ -3,7 +3,7 @@
let isRecording = false;
let websocket = null;
let recorder = null;
let chunkDuration = 1000;
let chunkDuration = 100;
let websocketUrl = "ws://localhost:8000/asr";
let userClosing = false;
let wakeLock = null;
@@ -269,9 +269,7 @@ function renderLinesWithBuffer(
speakerLabel = `<span class='loading'><span class="spinner"></span><span id='timeInfo'><span class="loading-diarization-value">${fmt1(
remaining_time_diarization
)}</span> second(s) of audio are undergoing diarization</span></span>`;
} else if (item.speaker == -1) {
speakerLabel = `<span id="speaker">Speaker 1<span id='timeInfo'>${timeInfo}</span></span>`;
} else if (item.speaker !== -1 && item.speaker !== 0) {
} else if (item.speaker !== 0) {
speakerLabel = `<span id="speaker">Speaker ${item.speaker}<span id='timeInfo'>${timeInfo}</span></span>`;
}