This commit is contained in:
Tamotsu Takahashi 2025-03-28 17:29:45 -04:00 committed by GitHub
commit 058a9264d4
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 11 additions and 0 deletions

View File

@ -408,6 +408,9 @@ extern "C" {
WHISPER_API const char * whisper_token_to_str(struct whisper_context * ctx, whisper_token token);
WHISPER_API const char * whisper_model_type_readable(struct whisper_context * ctx);
// String -> Token Id. Uses the vocabulary in the provided context
WHISPER_API bool whisper_token_exists(struct whisper_context * ctx, const char * str);
WHISPER_API whisper_token whisper_str_to_token(struct whisper_context * ctx, const char * str);
// Special tokens
WHISPER_API whisper_token whisper_token_eot (struct whisper_context * ctx);

View File

@ -4210,6 +4210,14 @@ const char * whisper_token_to_str(struct whisper_context * ctx, whisper_token to
return ctx->vocab.id_to_token.at(token).c_str();
}
whisper_token whisper_str_to_token(struct whisper_context * ctx, const char * str) {
return ctx->vocab.token_to_id.at(str);
}
bool whisper_token_exists(struct whisper_context * ctx, const char * str) {
return ctx->vocab.token_to_id.find(str) != ctx->vocab.token_to_id.end();
}
whisper_token whisper_token_eot(struct whisper_context * ctx) {
return ctx->vocab.token_eot;
}