8000 whisper : support speaker segmentation (local diarization) of mono audio via tinydiarize by akashmjn · Pull Request #1058 · ggml-org/whisper.cpp · GitHub
[go: up one dir, main page]
Skip to content

whisper : support speaker segmentation (local diarization) of mono audio via tinydiarize #1058

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 17 commits into from
Jul 4, 2023
+223 −138
Merged

whisper : support speaker segmentation (local diarization) of mono audio via tinydiarize #1058

Changes from 1 commit
Commits
Show all changes
17 commits
Select commit Hold shift + click to select a range
7f0dc9b
add HuggingFace mirror to download ggml model
akashmjn Jun 19, 2023
62c851b
support tdrz via simple hack overriding solm tokens
akashmjn Jun 19, 2023
c8e1ed6
fix incorrect translate/transcribe token_ids that are not static const
akashmjn Jun 19, 2023
700c282
add apollo 13 sample for tdrz demo
akashmjn Jun 20, 2023
4083a39
render [SPEAKER TURN] consistently in all terminal output using vocab…
akashmjn Jun 26, 2023
713c5b6
extend whisper_segment with speaker_turn_next field and save in json …
akashmjn Jun 27, 2023
edd2348
fix failing go build
akashmjn Jun 27, 2023
77825ec
slipped in some python syntax whoops
akashmjn Jun 28, 2023
12d3f90
Merge branch 'master' into tdrz-integrate-1
ggerganov Jul 2, 2023
024211f
Merge branch 'master' into tdrz-integrate-1
ggerganov Jul 3, 2023
59e9055
whisper : finalize tinydiarize support (add flag + fixes)
ggerganov Jul 3, 2023
8ee5af4
whisper : tdrz support for word-level timestamps (respect max_len)
ggerganov Jul 3, 2023
5fa32da
java : try to fix tests after adding tdrz_enable flag
ggerganov Jul 3, 2023
6828be7
main : remove TODO leftover
ggerganov Jul 3, 2023
09c32a6
java : fix params order list after adding "tdrz_enable"
ggerganov Jul 3, 2023
baabe2c
whisper : fix solm and add nosp token
ggerganov Jul 3, 2023
34bdf98
main : print tinydiarize help
ggerganov Jul 4, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Next Next commit
add HuggingFace mirror to download ggml model
  • Loading branch information
@akashmjn
akashmjn committed Jun 26, 2023
commit 7f0dc9bd6a7106dcfc033341f89e68a75b9ea5b1
8 changes: 7 additions & 1 deletion models/download-ggml-model.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@ function get_script_path() {
models_path="$(get_script_path)"

# Whisper models
models=( "tiny.en" "tiny" "base.en" "base" "small.en" "small" "medium.en" "medium" "large-v1" "large" )
models=( "tiny.en" "tiny" "base.en" "base" "small.en" "small.en-tdrz" "small" "medium.en" "medium" "large-v1" "large" )

# list available models
function list_models {
Expand Down Expand Up @@ -50,6 +50,12 @@ if [[ ! " ${models[@]} " =~ " ${model} " ]]; then
exit 1
fi

# check if model contains `tdrz` and update the src and pfx accordingly
if [[ $model == *"tdrz"* ]]; then
src="https://huggingface.co/akashmjn/tinydiarize-whisper.cpp"
pfx="resolve/main/ggml"
fi

# download ggml model

printf "Downloading ggml model $model from '$src' ...\n"
Expand Down
0