haraldwolff
/
whisper.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

main : escape quotes in csv output (#815)

pull/659/merge
Laytan Laats 2023-04-23 18:01:59 +02:00 committed by GitHub
parent 02ec83c5d5
commit 70567eff23
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 24 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

47
examples/main/main.cpp
View File

@ -352,29 +352,6 @@ bool output_srt(struct whisper_context * ctx, const char * fname, const whisper_
return true;
}
bool output_csv(struct whisper_context * ctx, const char * fname) {
std::ofstream fout(fname);
if (!fout.is_open()) {
fprintf(stderr, "%s: failed to open '%s' for writing\n", __func__, fname);
return false;
}
fprintf(stderr, "%s: saving output to '%s'\n", __func__, fname);
const int n_segments = whisper_full_n_segments(ctx);
fout << "start,end,text\n";
for (int i = 0; i < n_segments; ++i) {
const char * text = whisper_full_get_segment_text(ctx, i);
const int64_t t0 = whisper_full_get_segment_t0(ctx, i);
const int64_t t1 = whisper_full_get_segment_t1(ctx, i);
//need to multiply times returned from whisper_full_get_segment_t{0,1}() by 10 to get milliseconds.
fout << 10 * t0 << "," << 10 * t1 << ",\"" << text << "\"\n";
}
return true;
}
char *escape_double_quotes_and_backslashes(const char *str) {
if (str == NULL) {
return NULL;
@ -406,6 +383,30 @@ char *escape_double_quotes_and_backslashes(const char *str) {
return escaped;
}
bool output_csv(struct whisper_context * ctx, const char * fname) {
std::ofstream fout(fname);
if (!fout.is_open()) {
fprintf(stderr, "%s: failed to open '%s' for writing\n", __func__, fname);
return false;
}
fprintf(stderr, "%s: saving output to '%s'\n", __func__, fname);
const int n_segments = whisper_full_n_segments(ctx);
fout << "start,end,text\n";
for (int i = 0; i < n_segments; ++i) {
const char * text = whisper_full_get_segment_text(ctx, i);
const int64_t t0 = whisper_full_get_segment_t0(ctx, i);
const int64_t t1 = whisper_full_get_segment_t1(ctx, i);
char * text_escaped = escape_double_quotes_and_backslashes(text);
//need to multiply times returned from whisper_full_get_segment_t{0,1}() by 10 to get milliseconds.
fout << 10 * t0 << "," << 10 * t1 << ",\"" << text_escaped << "\"\n";
}
return true;
}
bool output_json(struct whisper_context * ctx, const char * fname, const whisper_params & params) {
std::ofstream fout(fname);
int indent = 0;