talk, talk-llama : pass text_to_speak as a file (#1865) 3fd8b4d unverified Tamotsu Takahashi commited on Feb 24, 2024
server : implement "verbose_json" format with token details (#1781) d6e13b6 unverified rmmh commited on Jan 18, 2024
whisper : add full CUDA and Metal offloading (#1472) da4acca unverified ggerganov HF Staff commited on Nov 12, 2023
sync : ggml (backend v2, k-quants, CUDA opts, Metal opts, etc.) (#1422) 7006035 unverified ggerganov HF Staff Chris Raethke commited on Nov 3, 2023
examples : move wav_writer from stream.cpp to common.h (#1317) 6c20dfb unverified bobqianic commited on Oct 3, 2023
ggml : sync (ggml-alloc, GPU, eps, etc.) (#1220) d41ba35 unverified ggerganov HF Staff commited on Sep 5, 2023
whisper : minor OpenVINO refactoring (#1037) fc78e6a unverified ggerganov HF Staff commited on Jul 4, 2023
ggml : sync latest repo (mostly refactoring changes) d97fd69 unverified ggerganov HF Staff commited on Jul 2, 2023
examples : fix + refactor Levenshtein distance 97f9410 unverified ggerganov HF Staff commited on Apr 30, 2023
whisper : add integer quantization support (#540) a5f8f3c unverified ggerganov HF Staff commited on Apr 30, 2023
examples : refactor in order to reuse code and reduce duplication (#482) acbd6f7 unverified ggerganov HF Staff commited on Feb 15, 2023