yjyoon / whisper_server_speaches star
slaesh 2024-08-31
Update script.sh 
somehow this missing "-" makes a huge difference.. :)
@96aef06868c6b2947533aab08212e5b48b18c30c
55761d5
96aef06
examples/live-audio/script.sh
--- examples/live-audio/script.sh
+++ examples/live-audio/script.sh
@@ -14,6 +14,6 @@
 
 # or you can run it on a CPU
 
 # docker run --detach --publish 8000:8000 --volume ~/.cache/huggingface:/root/.cache/huggingface --env WHISPER__MODEL=$WHISPER__MODEL fedirz/faster-whisper-server:latest-cpu
 
 
-# `pv` is used to limit the rate at which the audio is streamed to the server. Audio is being streamed at a rate of 32kb/s(16000 sample rate * 16-bit sample / 8 bits per byte = 32000 bytes per second). This emulutes live audio input from a microphone: `ffmpeg -loglevel quiet -f alsa -i default -ac 1 -ar 16000 -f s16le`
 
+# `pv` is used to limit the rate at which the audio is streamed to the server. Audio is being streamed at a rate of 32kb/s(16000 sample rate * 16-bit sample / 8 bits per byte = 32000 bytes per second). This emulutes live audio input from a microphone: `ffmpeg -loglevel quiet -f alsa -i default -ac 1 -ar 16000 -f s16le -`
 
 # shellcheck disable=SC2002
 
 cat audio.pcm | pv -qL 32000 | websocat --no-close --binary 'ws://localhost:8000/v1/audio/transcriptions?language=en'
Add a comment
List