Pinned issues
Issues
- 2
Request: provide Openvino models
#1893 opened by BBBalls - 3
Finetuning models for audio_ctx support
#1951 opened by abb128 - 1
whisper : adapt to latest ggml changes
#1959 opened by ggerganov - 1
perf regression compared with v1.4.0
#1958 opened by knitvoger - 0
Doing auto translations
#1957 opened by bharatModiIsMe - 7
100% crash when calling whisper_init_from_file_with_params with Address Sanitizer enabled (Xcode, ggml-large-v2) on both use_gpu={0,1}
#1885 opened by ronyfadel - 0
Translate to any language with forced decoding?
#1956 opened by luquitared - 1
- 1
Incorrect Transcription Language Output When Specifying Japanese Audio Input
#1935 opened by donwang-ux - 0
main.exe refuses to transcribe files with non-English characters in their file path
#1955 opened by hopto-dot - 2
Can the warehouse calculation section add support for rk3568 and rk3588NPU interfaces. Currently, the CPU processing speed is too slow
#1936 opened by jackwenshann - 1
Error when compiling with CuBLAS
#1950 opened by ClaraSev1 - 3
- 2
Compilation / distribution of a whisper.dll that 'just works' and is performant across all x86 processors, whether they support AVX2 extensions or not
#1939 opened by RyanMetcalfeInt8 - 2
Fine-tuned model (new language)
#1927 opened by zhusupaidai - 2
Zero-filled WAV give hallucination and wrong duration
#1881 opened by ukolovda - 4
- 2
Add time frames
#1919 opened by DittmerOk - 0
Android example: Why do we drop the lowest frequency cores instead of only selecting the highest frequency cores for the selection of the number of threads?
#1937 opened by soupslurpr - 2
OpenCL clGetPlatformIDs error
#1920 opened by devcxl - 4
error "linker command failed" when building the application made with go bindings
#1899 opened by arshamalh - 3
android or iOS Example Streaming support?
#1931 opened by Hynsn - 0
How to use CUDA acceleration for go-Whisper
#1946 opened by pony5551 - 7
- 7
- 2
- 2
Move grammar support out of examples? Unify?
#1930 opened by josharian - 4
CUDA on Windows
#1922 opened by jwijffels - 6
- 1
- 1
no output file is being written
#1923 opened by sysadminpower2019 - 0
Can the Whisper model be converted to rknn format and can corresponding support be provided
#1918 opened by jackwenshann - 0
failed to allocate buffer
#1915 opened by Hidend - 3
CoreML on M1 gives a wrong transcription
#1901 opened by nbarrera - 0
Compile with NVIDIA GPU support not working
#1906 opened by paelnever - 0
Integrate on SwiftUI App
#1912 opened by zydeico - 0
stream tool occurs error
#1908 opened by Honei - 0
Support for WhisperSpeech voice cloning
#1907 opened by danemadsen - 0
Whisper WASM not working
#1905 opened by yukiarimo - 3
Add support for 1.5, 2 and 3 bit quantization
#1900 opened by bil-ash - 2
talk-llama crash during initialization with opencl and NVIDIA GeForce GT 755M
#1896 opened by petterreinholdtsen - 1
-owts creates a rec16.wav.wts but it's empty
#1904 opened by theSoberSobber - 0
The peculiar behavior of matrix multiplication in CoreML. (I want to know if anyone has encountered the same issue as me.)
#1903 opened by tqtifnypmb - 2
libcuda.so.1 not found inside CUDA Container
#1879 opened by tiagofassoni - 0
info on Python binding
#1892 opened by daddym85 - 3
command app for chinese
#1884 opened by joyhope - 1
Is it possible to disable the word normalization?
#1883 opened by silvioprog - 1
Trouble building whisper.cpp with OpenVINO
#1882 opened by black-born - 2
talk-llama not buildable
#1880 opened by Exw27 - 0
not big endian safe
#1877 opened by maribu