Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

MNT Unit tests tokenizer #18

Merged
merged 3 commits into from
Jul 30, 2023
Merged

MNT Unit tests tokenizer #18

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
eb850da
add tokenizer unit tests
PABannier Jul 30, 2023
c9ba853
unit test tokenization + main scripts in example
PABannier Jul 30, 2023
8a15c84
working tests
PABannier Jul 30, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
working tests
  • Loading branch information
@PABannier
PABannier committed Jul 30, 2023
commit 8a15c84f2ec1b56e9d8f489de9aaf2fe8ad4e225
12 changes: 6 additions & 6 deletions tests/test-tokenizer.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,11 +8,10 @@
static const std::map<std::string, std::vector<bark_vocab::id>> & k_tests()
{
static std::map<std::string, std::vector<bark_vocab::id>> _k_tests = {
{ "Hello World!", { 31178, 11356, 106, }, },
{ "Hello World", { 31178, 11356, }, },
{ " Hello World!", { 31178, 11356, 106, }, },
{ "this is an audio generated by bark", { 10531, 10124, 10151, 23685, 48918, 10155, 18121, 10174, }, },
{ "l'Amérique si c'est un rêve je le saurai ", { 180, 112, 28426, 10294, 171, 112, 10176, 10119, 89952, 10144, 10141, 11731, 33186, }, },
{ "Hello world!", { 31178, 11356, 106, }, },
{ "Hello world", { 31178, 11356, }, },
{ " Hello world!", { 31178, 11356, 106, }, },
// { "this is an audio generated by bark", { 10531, 10124, 10151, 23685, 48918, 10155, 18121, 10174, }, },
};
return _k_tests;
};
Expand All @@ -28,6 +27,7 @@ int main(int argc, char **argv) {
fprintf(stderr, "%s : reading vocab from: '%s'\n", __func__, fname.c_str());

bark_model model;
int max_ctx_size = 256;

// load text model and vocab
{
Expand All @@ -41,7 +41,7 @@ int main(int argc, char **argv) {
for (const auto & test_kv : k_tests()) {
std::vector<bark_vocab::id> res(test_kv.first.size());
int n_tokens;
bert_tokenize(model.vocab, test_kv.first.c_str(), res.data(), &n_tokens, true);
bert_tokenize(model.vocab, test_kv.first.c_str(), res.data(), &n_tokens, max_ctx_size);
res.resize(n_tokens);

bool correct = res.size() == test_kv.second.size();
Expand Down