ggerganov
Follow
Pinned
858 contributions in the last year
Less
More
Contribution activity
November 2022
Created 97 commits in 4 repositories
Created 1 repository
Created a pull request in ggerganov/whisper.cpp that received 10 comments
Real-time streaming
[WIP in progress]
With the idea in #137 it is possible to reduce the time in the encoder multiple times.
This is beneficial for the stream example,…
+80
−23
•
10
comments
Opened 7 other pull requests in 1 repository
Reviewed 12 pull requests in 1 repository
ggerganov/whisper.cpp
12 pull requests
- improve livestream script
- Add AVX support, inline to ggml_fp16_to_fp32, ggml_fp16_t ggml_fp32_to_fp16 and some Makefile changes
- Build with OpenBLAS and SDL2 on windows
- Prompt previous tokens for streaming
- Update download-ggml-model.sh
- Add WHISPER_NO_AVX and WHISPER_NO_AVX2 to CMakeLists
- Support for stdin pipe stream
- Check for AVX and AVX2 on Darwin
- Fix the Windows pthread_create shim (Assertion failed: rc == 0)
- Try to add AVX 512-bit support
- Allow building with Accelerate for x86_64 Macs
- Cross compilation
Created an issue in ggerganov/whisper.cpp that received 4 comments
Voice assistant example - the "command" tool
There seems to be significant interest for a voice assistant application of Whisper, similar to "Ok, Google", "Hey Siri", "Alexa", etc. The existing …
4
comments
Opened 5 other issues in 2 repositories
ggerganov/whisper.cpp
2
open
2
closed
pluja/web-whisper
1
open
Started 4 discussions in 1 repository
ggerganov/whisper.cpp
ggerganov/whisper.cpp
-
Voice assistant example - the "command" tool
This contribution was made on Nov 23
-
Real-time transcription on Raspberry Pi 4
This contribution was made on Nov 21
-
Talk = GPT-2 + Whisper + WASM
This contribution was made on Nov 17
-
F.A.Q.
This contribution was made on Nov 6