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

* add HuggingFace mirror to download  ggml model

* support tdrz via simple hack overriding solm tokens

* fix incorrect translate/transcribe token_ids that are not static const

* add apollo 13 sample for tdrz demo

* render [SPEAKER TURN] consistently in all terminal output using vocab.id_to_token

* extend whisper_segment with speaker_turn_next field and save in json output

* fix failing go build

* slipped in some python syntax whoops

* whisper : finalize tinydiarize support (add flag + fixes)

* whisper : tdrz support for word-level timestamps (respect max_len)

* java : try to fix tests after adding tdrz_enable flag

* main : remove TODO leftover

* java : fix params order list after adding "tdrz_enable"

* whisper : fix solm and add nosp token

* main : print tinydiarize help

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

models/download-ggml-model.sh

@@ -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 {
@@ -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"