From 184e9a43b82c96fadecd97f1fd40006ed7c80f50 Mon Sep 17 00:00:00 2001 From: Dina Suehiro Jones Date: Sun, 20 Oct 2024 19:22:22 -0700 Subject: [PATCH] Update AudioQnA README to add a couple usage details (#948) Signed-off-by: Dina Suehiro Jones Co-authored-by: Sihan Chen <39623753+Spycsh@users.noreply.github.com> --- AudioQnA/docker_compose/intel/cpu/xeon/README.md | 4 ++++ AudioQnA/docker_compose/intel/hpu/gaudi/README.md | 8 +++++++- 2 files changed, 11 insertions(+), 1 deletion(-) diff --git a/AudioQnA/docker_compose/intel/cpu/xeon/README.md b/AudioQnA/docker_compose/intel/cpu/xeon/README.md index 29440d086..4f375464d 100644 --- a/AudioQnA/docker_compose/intel/cpu/xeon/README.md +++ b/AudioQnA/docker_compose/intel/cpu/xeon/README.md @@ -127,6 +127,10 @@ curl http://${host_ip}:3002/v1/audio/speech \ ## 🚀 Test MegaService +Test the AudioQnA megaservice by recording a .wav file, encoding the file into the base64 format, and then sending the +base64 string to the megaservice endpoint. The megaservice will return a spoken response as a base64 string. To listen +to the response, decode the base64 string and save it as a .wav file. + ```bash curl http://${host_ip}:3008/v1/audioqna \ -X POST \ diff --git a/AudioQnA/docker_compose/intel/hpu/gaudi/README.md b/AudioQnA/docker_compose/intel/hpu/gaudi/README.md index 842227ee5..7f08fe5ad 100644 --- a/AudioQnA/docker_compose/intel/hpu/gaudi/README.md +++ b/AudioQnA/docker_compose/intel/hpu/gaudi/README.md @@ -79,6 +79,8 @@ export LLM_SERVICE_PORT=3007 ## 🚀 Start the MegaService +> **_NOTE:_** Users will need at least three Gaudi cards for AudioQnA. + ```bash cd GenAIExamples/AudioQnA/docker_compose/intel/hpu/gaudi/ docker compose up -d @@ -127,9 +129,13 @@ curl http://${host_ip}:3002/v1/audio/speech \ ## 🚀 Test MegaService +Test the AudioQnA megaservice by recording a .wav file, encoding the file into the base64 format, and then sending the +base64 string to the megaservice endpoint. The megaservice will return a spoken response as a base64 string. To listen +to the response, decode the base64 string and save it as a .wav file. + ```bash curl http://${host_ip}:3008/v1/audioqna \ -X POST \ -d '{"audio": "UklGRigAAABXQVZFZm10IBIAAAABAAEARKwAAIhYAQACABAAAABkYXRhAgAAAAEA", "max_tokens":64}' \ - -H 'Content-Type: application/json' + -H 'Content-Type: application/json' | sed 's/^"//;s/"$//' | base64 -d > output.wav ```