ggerganov/whisper.cpp

Issues

• Error when initializing context from Java

  #2223 opened a day ago
  0

• Loading Whisperkit model via dropdown (top right) does not give warning about initial model activation

  #2222 opened a day ago
  1

• [Question] Does Whisper.cpp support Flash Attention V2?

  #2219 opened 2 days ago
  0

• WHISPER_CUDA compile error

  #2218 opened 2 days ago
  0

• CUBLAS CMAKE issue

  #2216 opened 3 days ago
  0

• Nonsense Output At times in spite of silence

  #2215 opened 3 days ago
  0

• Cuda doesn't use nvidia GPU

  #2214 opened 4 days ago
  0

• Dell Inspiron 5593 Intel® Core™ i7-1065G7 CPU @ 1.30GHz × 8

  #2213 opened 4 days ago
  0

• apple M1 error

  #2211 opened 5 days ago
  0

• WASM examples could not fetch whisper models due to CORS

  #2210 opened 5 days ago
  0

• Add log callback for opencl

  #2209 opened 5 days ago
  0

• Optimized/fused kernels for GEMV with 4-bit quantized weights

  #2207 opened 6 days ago
  0

• Error with building on CUDA: Windows

  #2203 opened 7 days ago
  3

• Cmake: Unable to build on Windows with -DWHISPER_HIPBLAS=ON

  #2202 opened 8 days ago
  2

• GGML Concat function changed and now we get error

  #2201 opened 8 days ago
  1

• cmake can't find arch

  #2197 opened a day ago
  2

• Removing the `whisper_pcm_to_mel_phase_vocoder*` functions

  #2195 opened 9 days ago
  1

• Correct parameter for cross compile for ARM A55 with WebOS ?

  #2192 opened 11 days ago
  0

• Latest 1.6.2 release substantial increase in hallucinations for large-v3 on CUDA

  #2191 opened 11 days ago
  16

• Usage of deprecated OpenVINO packages under Python 3.12 prevents using OpenVINO models

  #2190 opened 12 days ago
  0

• Question: make -j4 ggml for seamlessM4T , "ggml_backend" is undefined

  #2188 opened 12 days ago
  0

• Disable avx / avx2 / fma / f16c at runtime

  #2187 opened 12 days ago
  0

• Degraded quality with timestamps disabled

  #2186 opened 12 days ago
  0

• Last version of ruby gem "whispercpp" cannot be build

  #2185 opened 14 days ago
  2

• can i use the fasterWhisper model?

  #2183 opened 15 days ago
  0

• JSON Output Contains Garbled Characters for Chinese Audio Transcription

  #2180 opened 15 days ago
  1

• Microphone not working?

  #2179 opened 15 days ago
  3

• Windows service crashes during inference

  #2178 opened 16 days ago
  5

• Crash with multiple whisper states running at the same time CUDA

  #2177 opened 13 days ago
  4

• Silent crash on Windows

  #2175 opened 18 days ago
  1

• 'stdbool.h' file not found

  #2174 opened 19 days ago
  0

• Different platforms return different results

  #2173 opened 19 days ago
  2

• Segmentation fault - Illegal instruction

  #2172 opened 20 days ago
  1

• Which binary should be used for mac m1?

  #2169 opened 21 days ago
  0