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>
This commit is contained in:
Akash Mahajan
2023-07-03 23:45:00 -07:00
committed by GitHub
parent fdf58a6668
commit c8d0f5fe98
8 changed files with 215 additions and 130 deletions

View File

@ -270,13 +270,13 @@ func (ctx *Context) Whisper_token_lang(lang_id int) Token {
}
// Task tokens
func Whisper_token_translate() Token {
return Token(C.whisper_token_translate())
func (ctx *Context) Whisper_token_translate() Token {
return Token(C.whisper_token_translate((*C.struct_whisper_context)(ctx)))
}
// Task tokens
func Whisper_token_transcribe() Token {
return Token(C.whisper_token_transcribe())
func (ctx *Context) Whisper_token_transcribe() Token {
return Token(C.whisper_token_transcribe((*C.struct_whisper_context)(ctx)))
}
// Performance information