Commit History

Author SHA1 Message Date
  Jong Wook Kim b5851c6c40 Update tokenizer.py (#1163) 1 year ago
  Jong Wook Kim 6dea21fd7f Release 20230314 2 years ago
  Jong Wook Kim 79c43e4859 abort find_alignment on empty input (#1090) 2 years ago
  Guillaume Klein 5f9ac653b7 Fix truncated words list when the replacement character is decoded (#1089) 2 years ago
  Akash Mahajan ba88b8e1b3 fix github language stats getting dominated by jupyter notebook (#1076) 2 years ago
  Guillaume Klein 671ac5a4ce Fix alignment between the segments and the list of words (#1087) 2 years ago
  Jong Wook Kim 839639a223 Use tiktoken (#1044) 2 years ago
  Jong Wook Kim ad3250a846 Release 20230308 2 years ago
  Jong Wook Kim c4b50c0824 kwargs in decode() for convenience (#1061) 2 years ago
  Jong Wook Kim 38f2f4d99d fix all_tokens handling that caused more repetitions and discrepancy in JSON (#1060) 2 years ago
  Jong Wook Kim aac47c9834 fix typo 2 years ago
  Jong Wook Kim 26807ec6d3 Release 20230307 2 years ago
  Jong Wook Kim 919a713499 attempt to fix the repetition/hallucination issue identified in #1046 (#1052) 2 years ago
  Jong Wook Kim 38e990d853 Use triton==2.0.0 (#1053) 2 years ago
  Jong Wook Kim 924e1f8e06 Try installing triton only if linux & x86_64 (#1051) 2 years ago
  Jong Wook Kim 4b0d5e58d0 Update setup.py 2 years ago
  Jong Wook Kim 8180fde939 Release 20230306 2 years ago
  Local State c6e4e5efb3 remove auxiliary audio extension (#1021) 2 years ago
  Jong Wook Kim b80bcf610d apply formatting with `black` (#1038) 2 years ago
  Jong Wook Kim 500d0fe966 word-level timestamps in `transcribe()` (#869) 2 years ago
  Jong Wook Kim eab8d920ed Decoding improvements (#1033) 2 years ago
  Roman Vasilenko 3e1780fd37 Update README.md (#894) 2 years ago
  Andrey Chernykh 7858aa9c08 Fix infinite loop caused by incorrect timestamp tokens prediction (#914) 2 years ago
  Jong Wook Kim 5c1a8c10e7 clarify that 3.11 is not supported 2 years ago
  Jong Wook Kim 4e635c6644 Update README.md about Python 3.8+ requirement 2 years ago
  Jong Wook Kim a6b36ede1f drop python 3.7 support (#889) 2 years ago
  Jong Wook Kim 55f690af79 Release 20230124 2 years ago
  Jong Wook Kim 7f1ef223ab handle printing even if sys.stdout.buffer is not available (#887) 2 years ago
  Niels Mayer f5bfe004ec Add TSV formatted output in transcript, using integer start/end times in milliseconds. (#228) 2 years ago
  Aaryan YVS da600abd2b Added --output_format option (#333) 2 years ago