whisper : add whisper_state + default state on the whisper_context (g…

…gerganov#523) * Added whisper state + default state on the whisper_context * Fixed some examples and bindings * Fixed whisper_n_len (which was used in some binding) and added whisper_n_len_from_state * Fixed comments * whisper : reuse kv_cache_free() and fix compiler warnings * whisper : clean-up the API comments --------- Co-authored-by: Sandro Hanea <[email protected]> Co-authored-by: Georgi Gerganov <[email protected]>
James3039 · Mar 5, 2023 · 59fdcd1 · 59fdcd1
1 parent 478289a
commit 59fdcd1
Show file tree

Hide file tree

Showing 6 changed files with 701 additions and 453 deletions.
diff --git a/bindings/go/whisper.go b/bindings/go/whisper.go
@@ -20,7 +20,7 @@ extern bool callEncoderBegin(void* user_data);
 // Text segment callback
 // Called on every newly generated text segment
 // Use the whisper_full_...() functions to obtain the text segments
-static void whisper_new_segment_cb(struct whisper_context* ctx, int n_new, void* user_data) {
+static void whisper_new_segment_cb(struct whisper_context* ctx, struct whisper_state* state, int n_new, void* user_data) {
     if(user_data != NULL && ctx != NULL) {
         callNewSegment(user_data, n_new);
     }
@@ -29,7 +29,7 @@ static void whisper_new_segment_cb(struct whisper_context* ctx, int n_new, void*
 // Encoder begin callback
 // If not NULL, called before the encoder starts
 // If it returns false, the computation is aborted
-static bool whisper_encoder_begin_cb(struct whisper_context* ctx, void* user_data) {
+static bool whisper_encoder_begin_cb(struct whisper_context* ctx, struct whisper_state* state, void* user_data) {
     if(user_data != NULL && ctx != NULL) {
         return callEncoderBegin(user_data);
     }

diff --git a/bindings/ruby/ext/ruby_whisper.cpp b/bindings/ruby/ext/ruby_whisper.cpp
@@ -199,7 +199,7 @@ static VALUE ruby_whisper_transcribe(int argc, VALUE *argv, VALUE self) {
   {
     static bool is_aborted = false; // NOTE: this should be atomic to avoid data race
 
-    rwp->params.encoder_begin_callback = [](struct whisper_context * /*ctx*/, void * user_data) {
+    rwp->params.encoder_begin_callback = [](struct whisper_context * /*ctx*/, struct whisper_state * /*state*/, void * user_data) {
       bool is_aborted = *(bool*)user_data;
       return !is_aborted;
     };

diff --git a/examples/addon.node/addon.cpp b/examples/addon.node/addon.cpp
@@ -72,7 +72,7 @@ int timestamp_to_sample(int64_t t, int n_samples) {
     return std::max(0, std::min((int) n_samples - 1, (int) ((t*WHISPER_SAMPLE_RATE)/100)));
 }
 
-void whisper_print_segment_callback(struct whisper_context * ctx, int n_new, void * user_data) {
+void whisper_print_segment_callback(struct whisper_context * ctx, struct whisper_state * state, int n_new, void * user_data) {
     const auto & params  = *((whisper_print_user_data *) user_data)->params;
     const auto & pcmf32s = *((whisper_print_user_data *) user_data)->pcmf32s;
 
@@ -260,7 +260,7 @@ int run(whisper_params &params, std::vector<std::vector<std::string>> &result) {
             {
                 static bool is_aborted = false; // NOTE: this should be atomic to avoid data race
 
-                wparams.encoder_begin_callback = [](struct whisper_context * /*ctx*/, void * user_data) {
+                wparams.encoder_begin_callback = [](struct whisper_context * /*ctx*/, struct whisper_state * /*state*/, void * user_data) {
                     bool is_aborted = *(bool*)user_data;
                     return !is_aborted;
                 };

diff --git a/examples/main/main.cpp b/examples/main/main.cpp
@@ -193,7 +193,7 @@ struct whisper_print_user_data {
     const std::vector<std::vector<float>> * pcmf32s;
 };
 
-void whisper_print_segment_callback(struct whisper_context * ctx, int n_new, void * user_data) {
+void whisper_print_segment_callback(struct whisper_context * ctx, struct whisper_state * /*state*/, int n_new, void * user_data) {
     const auto & params  = *((whisper_print_user_data *) user_data)->params;
     const auto & pcmf32s = *((whisper_print_user_data *) user_data)->pcmf32s;
 
@@ -608,7 +608,7 @@ int main(int argc, char ** argv) {
             {
                 static bool is_aborted = false; // NOTE: this should be atomic to avoid data race
 
-                wparams.encoder_begin_callback = [](struct whisper_context * /*ctx*/, void * user_data) {
+                wparams.encoder_begin_callback = [](struct whisper_context * /*ctx*/, struct whisper_state * /*state*/, void * user_data) {
                     bool is_aborted = *(bool*)user_data;
                     return !is_aborted;
                 };