Fix bug: RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (when checking argument for argument index in method wrapper__index_select)
* Add --threads option to transcribe
Torch on CPU uses by default number_of_cores/2. This option allows to
override this default.
* Update transcribe.py
Co-authored-by: Jong Wook Kim <ilikekjw@gmail.com>
* Use two-digit hours in WebVTT timestamps
Per the WebVTT specification [0]:
> A WebVTT timestamp consists of the following components, in the given
> order:
>
> 1. Optionally (required if hours is non-zero):
> 1. Two or more ASCII digits, representing the hours as a base ten
> integer.
> 2. A U+003A COLON character (:)
YouTube won’t accept timestamps containing single-digit hours.
[0] https://www.w3.org/TR/webvtt1/#webvtt-timestamp
* Strip segment text in WebVTT output
We already do this for plain text and SubRip output, so we should do it
for WebVTT too.
* Adds missing command for install (mac)
Required for users who didn't previously have Rust installed.
* minor wording change
Co-authored-by: Jong Wook Kim <jongwook@nyu.edu>
* Write each sentence as a separate line for the txt output
Write each sentence as a separate line for the txt output
* Update utils.py
Co-authored-by: EliEron <example@example.com>
Co-authored-by: Jong Wook Kim <jongwook@nyu.edu>
* add progress bar to transcribe loop
* improved warning message for English-only models
* add --condition_on_previous_text
* progressbar renames
Co-authored-by: Jong Wook Kim <jongwook@nyu.edu>
Before this change, the model is loaded into GPU regardless of the value of "device" argument in CLI.
(e.g. whisper "test.wav" --device cpu loads into GPU anyway)
* fix: more-itertools name in requirements.txt
* feature: minimal environment.yml for conda
* Revert "feature: minimal environment.yml for conda"
This reverts commit 8fd7438b368b0eb5df85f667fea911f293fa5e6d.
Co-authored-by: Jong Wook Kim <jongwook@nyu.edu>
