mirror of
https://github.com/ggerganov/whisper.cpp.git
synced 2024-12-18 20:27:53 +00:00
whisper : add whisper_token_count helper
This commit is contained in:
parent
5c2c07d479
commit
ba69578828
@ -3731,6 +3731,10 @@ int whisper_tokenize(struct whisper_context * ctx, const char * text, whisper_to
|
||||
return res.size();
|
||||
}
|
||||
|
||||
int whisper_token_count(struct whisper_context * ctx, const char * text) {
|
||||
return -whisper_tokenize(ctx, text, NULL, 0);
|
||||
}
|
||||
|
||||
int whisper_lang_max_id() {
|
||||
auto max_id = 0;
|
||||
for (const auto & kv : g_lang) {
|
||||
|
@ -345,6 +345,10 @@ extern "C" {
|
||||
whisper_token * tokens,
|
||||
int n_max_tokens);
|
||||
|
||||
// Return the number of tokens in the provided text
|
||||
// Equivalent to: -whisper_tokenize(ctx, text, NULL, 0)
|
||||
int whisper_token_count(struct whisper_context * ctx, const char * text);
|
||||
|
||||
// Largest language id (i.e. number of available languages - 1)
|
||||
WHISPER_API int whisper_lang_max_id();
|
||||
|
||||
@ -504,7 +508,7 @@ extern "C" {
|
||||
// tokens to provide to the whisper decoder as initial prompt
|
||||
// these are prepended to any existing text context from a previous call
|
||||
// use whisper_tokenize() to convert text to tokens
|
||||
// maximum of whisper_n_text_ctx()/2 tokens are used
|
||||
// maximum of whisper_n_text_ctx()/2 tokens are used (typically 224)
|
||||
const char * initial_prompt;
|
||||
const whisper_token * prompt_tokens;
|
||||
int prompt_n_tokens;
|
||||
|
Loading…
Reference in New Issue
Block a user