Commit Graph

  • 164df0d447 whisper.objc : fix context + broken readme links Georgi Gerganov 2022-11-27 10:48:59 +02:00
  • e266cb0723 whisper.objc : add real-time processing (#97) Georgi Gerganov 2022-11-26 17:28:28 +02:00
  • c207eed431 whisper.objc : fix build warnings Georgi Gerganov 2022-11-26 16:27:04 +02:00
  • 67e819baf4 minor : remove "examples/" prefix from the README Georgi Gerganov 2022-11-26 13:07:54 +02:00
  • a425365b82 yt-wsp.sh : script to easily transcribe VODs Georgi Gerganov 2022-11-26 12:53:23 +02:00
  • e0e864d9ca Update README.md Georgi Gerganov 2022-11-26 11:56:55 +02:00
  • 68ecadbbc9 command.wasm : add voice assistant example for the Web (#171) Georgi Gerganov 2022-11-26 11:40:06 +02:00
  • c536ff4005 minor : add comment for using "generate_karaoke.sh" Georgi Gerganov 2022-11-26 10:22:42 +02:00
  • cb70b07db5 livestream.sh : simple tool to transcribe audio livestreams (#185) Georgi Gerganov 2022-11-26 10:05:37 +02:00
  • 3c390ffe38 stream.wasm : add web-based real-time transcription (#112) Georgi Gerganov 2022-11-25 23:57:46 +02:00
  • be16dfa038 whisper.wasm : do not block page while processing (close #86) Georgi Gerganov 2022-11-25 23:07:42 +02:00
  • 0f619b52ce main : add stereo-channel-based diarization (#64) Georgi Gerganov 2022-11-25 22:08:58 +02:00
  • 1246dd023e command : add demonstration video Georgi Gerganov 2022-11-25 20:23:58 +02:00
  • 0be27bbd92 command : fix build + fix README + add bold printing Georgi Gerganov 2022-11-25 19:53:50 +02:00
  • bc88eb13c6 examples : add "command" tool (#171) Georgi Gerganov 2022-11-25 19:06:56 +02:00
  • b8ce25dec1 refactoring : more readable code Georgi Gerganov 2022-11-25 19:08:51 +02:00
  • fd113687aa correct model name display on running samples vicalloy 2022-11-25 11:24:08 +08:00
  • e4805d9601 wasm : refactor wasm example + reuse fetch mechanism Georgi Gerganov 2022-11-24 23:13:26 +02:00
  • ff36415a86 talk.wasm : update video link + some minor fixes Georgi Gerganov 2022-11-24 20:15:07 +02:00
  • 025ff465b6 Update README.md Georgi Gerganov 2022-11-24 20:09:45 +02:00
  • 2c0501b38a Update README.md Georgi Gerganov 2022-11-24 20:06:51 +02:00
  • abce28ea99 talk.wasm : move to https://whisper.ggerganov.com/talk Georgi Gerganov 2022-11-24 18:24:06 +02:00
  • a2ecd54455 models : add instructions for using HF fine-tuned models Georgi Gerganov 2022-11-24 17:54:41 +02:00
  • 128aaadb93 whisper : improve printfs Georgi Gerganov 2022-11-24 17:54:16 +02:00
  • 454b91de16 main : fix dangling pointer when using stdin for input (#65) Georgi Gerganov 2022-11-24 17:53:51 +02:00
  • d7024cf9dc main, stream : remove --verbose flag (#178) Georgi Gerganov 2022-11-24 17:52:04 +02:00
  • 37422ed733 talk.wasm : add audio pre-processing + bump memory Georgi Gerganov 2022-11-24 00:34:00 +02:00
  • be3b720f96 talk.wasm : refactoring + update README.md Georgi Gerganov 2022-11-24 00:08:57 +02:00
  • 00f46dbc1d models : add usage comments to the HF convert script (#157) Georgi Gerganov 2022-11-23 23:22:40 +02:00
  • 5698bddbc9 models : fix HF fine-tuned model conversion script (#157) Georgi Gerganov 2022-11-23 23:14:11 +02:00
  • 388e9f79ad ggml : fix the fix Georgi Gerganov 2022-11-23 22:40:06 +02:00
  • 35cd29ce1f ggml : fix cross-compile Linux -> Window with mingw (#168) Georgi Gerganov 2022-11-23 22:27:49 +02:00
  • a156a358ca Revert "update README.md" Georgi Gerganov 2022-11-23 22:16:50 +02:00
  • 6a84147113 update README.md katsu560 2022-11-23 22:59:54 +09:00
  • 804f36aa2c ggml: change inline ggml_fp16_to_fp32, ggml_fp16_t ggml_fp32_to_fp16 katsu560 2022-11-23 22:54:21 +09:00
  • 4b2f51b479 add gprof option katsu560 2022-11-23 21:31:05 +09:00
  • 800ae5b808 fix AVX,AVX2,FMA,F16C detection on Linux and add flags for OpenBLAS katsu560 2022-11-23 20:23:35 +09:00
  • 83456076f0 add AVX support katsu560 2022-11-23 20:23:24 +09:00
  • 3df6c14fca Build with OpenBLAS and SDL2 on windows Tamotsu Takahashi 2022-11-23 15:17:13 +09:00
  • d64d6ca3fd models : minor changes to the HF convert script (#157) Georgi Gerganov 2022-11-23 22:07:20 +02:00
  • 93482d0373 models : add "convert-h5-to-ggml.py" script (#157) Georgi Gerganov 2022-11-23 17:17:31 +02:00
  • 49706a658a minor : updates few prints + fix buttons in whisper.wasm Georgi Gerganov 2022-11-23 17:17:01 +02:00
  • 363a2dadec Update README.md Georgi Gerganov 2022-11-23 09:53:55 +02:00
  • 623a486056 Update README.md Georgi Gerganov 2022-11-23 09:52:36 +02:00
  • 2f596f5b33 Find libopenblas.dll.a on windows Tamotsu Takahashi 2022-11-23 09:46:56 +09:00
  • e5dcdabbb8 unicode : fix character replacement (thanks to @tamo) Georgi Gerganov 2022-11-23 08:24:29 +02:00
  • dad109c3f1 close #109 : add fetching of the model over HTTP (whisper.wasm) Georgi Gerganov 2022-11-22 22:48:56 +02:00
  • 326573de9a talk.wasm : final touches Georgi Gerganov 2022-11-22 22:22:17 +02:00
  • 9aea96f774 talk.wasm : polishing + adding many AI personalities Georgi Gerganov 2022-11-22 20:10:20 +02:00
  • 385236d1d3 stream : "-kc" now enables context keeping from previous segment (#90) Georgi Gerganov 2022-11-22 18:20:05 +02:00
  • 63ae03b8e0 Prompt previous tokens for streaming (#163) M. Eren Akbiyik 2022-11-22 17:10:35 +01:00
  • 78116f8eda talk.wasm : update README.md Georgi Gerganov 2022-11-21 22:42:29 +02:00
  • a4dfbeecf9 talk.wasm : GPT-2 meets Whisper in WebAssembly (#155) Georgi Gerganov 2022-11-21 22:20:42 +02:00
  • 2e311a2917 Update README.md Georgi Gerganov 2022-11-21 18:52:20 +02:00
  • 2065572a11 ggml : fix Windows build Georgi Gerganov 2022-11-20 22:43:32 +02:00
  • 5c2176e314 ci : add Windows build Georgi Gerganov 2022-11-20 22:39:39 +02:00
  • f2df9bd768 stream : add "max_tokens" cli arg Georgi Gerganov 2022-11-20 21:22:02 +02:00
  • fb8d77f760 stream : add "audio_ctx" parameter Georgi Gerganov 2022-11-20 21:12:01 +02:00
  • 62b5ff875c stream : add "max_tokens" parameter Georgi Gerganov 2022-11-20 20:52:24 +02:00
  • d351771a4b stream : add "single_segment" option Georgi Gerganov 2022-11-20 20:45:10 +02:00
  • c058aaf22e stream : partial encoder experiments Georgi Gerganov 2022-11-11 22:33:10 +02:00
  • 2ba66360c9 fix: free ggml_context (close #149) (#150) greeshmay 2022-11-17 12:12:51 -08:00
  • e70e5c8b53 models : simplify the conversion script Georgi Gerganov 2022-11-16 19:21:43 +02:00
  • 55a0e1a64e Update download-ggml-model.sh Dody Suria Wijaya 2022-11-16 23:53:01 +07:00
  • 864a78a8d0 models : change default hosting to Hugging Face Georgi Gerganov 2022-11-15 19:47:06 +02:00
  • 83c742f1a7 whisper : add option to speed up the audio tempo by x2 Georgi Gerganov 2022-11-12 18:03:49 +02:00
  • 41b48ab7f1 make : add libwhisper.so target (#144) Georgi Gerganov 2022-11-13 09:08:33 +02:00
  • a728be9cdb Add WHISPER_NO_AVX and WHISPER_NO_AVX2 to CMakeLists (#136) Chidi Williams 2022-11-11 16:10:01 +00:00
  • 46a68fb9b5 minor : remove one more redundant line Georgi Gerganov 2022-11-11 18:02:58 +02:00
  • ccd56a9c5b minor : fix double float32 conversion in python script Georgi Gerganov 2022-11-11 17:58:51 +02:00
  • 3500ce8727 ref #40 : start working on the documentation Georgi Gerganov 2022-11-09 21:41:21 +02:00
  • 7519eabf65 Adds support for stdin wav input Alan 2022-11-09 15:24:06 -03:00
  • b21213c23e js : update whipser.js to latest Georgi Gerganov 2022-11-09 19:32:58 +02:00
  • 9e700e1821 Check for AVX and AVX2 on Darwin Chidi Williams 2022-11-09 00:28:36 +00:00
  • 0bfe728b84 Fix the Windows pthread_create shim boolemancer 2022-11-08 03:04:23 -08:00
  • 4e5674a5d5 sync : submodule whisper.spm Georgi Gerganov 2022-11-07 21:48:13 +02:00
  • 4c66b6a828 cmake : add submodule whisper.spm Georgi Gerganov 2022-11-07 20:50:24 +02:00
  • c30bffc8a5 ref #22 : add "duration" option Georgi Gerganov 2022-11-07 20:14:52 +02:00
  • 8fdfb0ba92 Update README.md Georgi Gerganov 2022-11-06 21:04:21 +02:00
  • c71363f14c examples : add simple script for generating Karaoke video Georgi Gerganov 2022-11-06 09:22:50 +02:00
  • a09e9123ca Update README.md Georgi Gerganov 2022-11-05 08:44:41 +02:00
  • d42cf6d0df Update README.md Georgi Gerganov 2022-11-04 22:26:08 +02:00
  • ef47d77492 main : fix generated bash script Georgi Gerganov 2022-11-04 18:30:38 +02:00
  • 75171c2b79 ggml : multi-thread the ggml_add operator Georgi Gerganov 2022-11-03 20:53:44 +02:00
  • a2eeb941f6 cmake : fix passing GGML_PERF compile option Georgi Gerganov 2022-11-03 20:18:57 +02:00
  • 0e689f83d8 Update README.md Georgi Gerganov 2022-11-02 22:03:27 +02:00
  • d5afebd37c whisper : token-level timestamp refactoring (#49, #120) Georgi Gerganov 2022-11-02 21:18:20 +02:00
  • 4b1c32e8ea Update README.md Georgi Gerganov 2022-11-02 18:33:29 +02:00
  • b5dde365e9 extra : compute SHA of all models files Georgi Gerganov 2022-11-02 18:31:55 +02:00
  • 02dfd5b8c3 whisper : fix extra memory usage after recent processor changes Georgi Gerganov 2022-11-02 18:31:18 +02:00
  • c63ce24834 Allow building with Accelerate for x86_64 Macs (#123) Syed Jafri 2022-11-02 10:00:19 -06:00
  • 137321915f ggml : fix the check for NEON support (#7) Georgi Gerganov 2022-11-02 17:52:24 +02:00
  • 24cd12f647 Cross compilation (#121) Syed Jafri 2022-11-02 00:46:49 -06:00
  • e46bc56e71 Update README.md Georgi Gerganov 2022-11-01 22:47:58 +02:00
  • 6fb98370ba main : add some comments for the word-level timestamp algorithm Georgi Gerganov 2022-11-01 22:35:21 +02:00
  • 0729da9a3b main : fix some edge cases for word-level timestamps Georgi Gerganov 2022-11-01 22:09:25 +02:00
  • 5dc74e3aff Update README.md Georgi Gerganov 2022-10-31 22:06:05 +02:00
  • ac8ef34039 Update README.md Georgi Gerganov 2022-10-31 20:19:41 +02:00
  • b26345cc7b Added for Windows implemenated script download-ggml-model.cmd Mikhail Grigorev 2022-10-31 00:51:29 +05:00
  • 8dac3c6e10 Fixed sched_yield Mikhail Grigorev 2022-10-30 22:19:24 +05:00