ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2024-12-18 20:27:53 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

talk.wasm : bump memory usage + update whisper.js

Browse Source
This commit is contained in:
Georgi Gerganov 2023-01-06 21:12:51 +02:00
parent 41e05c6b1b
commit 87dd4a3081
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
3 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
bindings/javascript/whisper.js
View File

File diff suppressed because one or more lines are too long

4
examples/talk.wasm/CMakeLists.txt
View File

@ -33,8 +33,8 @@ set_target_properties(${TARGET} PROPERTIES LINK_FLAGS " \
--bind \ --bind \
-s USE_PTHREADS=1 \ -s USE_PTHREADS=1 \
-s PTHREAD_POOL_SIZE=8 \ -s PTHREAD_POOL_SIZE=8 \
-s INITIAL_MEMORY=1600MB \ -s INITIAL_MEMORY=1800MB \
-s TOTAL_MEMORY=1600MB \ -s TOTAL_MEMORY=1800MB \
-s FORCE_FILESYSTEM=1 \ -s FORCE_FILESYSTEM=1 \
-s EXPORTED_RUNTIME_METHODS=\"['print', 'printErr', 'ccall', 'cwrap']\" \ -s EXPORTED_RUNTIME_METHODS=\"['print', 'printErr', 'ccall', 'cwrap']\" \
${EXTRA_FLAGS} \ ${EXTRA_FLAGS} \

2
examples/talk.wasm/README.md
View File

@ -36,7 +36,7 @@ In order to run this demo efficiently, you need to have the following:
- Latest Chrome or Firefox browser (Safari is not supported) - Latest Chrome or Firefox browser (Safari is not supported)
- Run this on a desktop or laptop with modern CPU (a mobile phone will likely not be good enough) - Run this on a desktop or laptop with modern CPU (a mobile phone will likely not be good enough)
- Speak phrases that are no longer than 10 seconds - this is the audio context of the AI - Speak phrases that are no longer than 10 seconds - this is the audio context of the AI
- The web-page uses about 1.6GB of RAM - The web-page uses about 1.8GB of RAM
Notice that this demo is using the smallest GPT-2 model, so the generated text responses are not always very good. Notice that this demo is using the smallest GPT-2 model, so the generated text responses are not always very good.
Also, the prompting strategy can likely be improved to achieve better results. Also, the prompting strategy can likely be improved to achieve better results.