| | |
| | | return mm; |
| | | } |
| | | |
| | | _FUNASRAPI FUNASR_HANDLE FunOfflineInit(std::map<std::string, std::string>& model_path, int thread_num) |
| | | _FUNASRAPI FUNASR_HANDLE FunOfflineInit(std::map<std::string, std::string>& model_path, int thread_num, bool use_gpu, int batch_size) |
| | | { |
| | | funasr::OfflineStream* mm = funasr::CreateOfflineStream(model_path, thread_num); |
| | | funasr::OfflineStream* mm = funasr::CreateOfflineStream(model_path, thread_num, use_gpu, batch_size); |
| | | return mm; |
| | | } |
| | | |
| | |
| | | if (!recog_obj) |
| | | return nullptr; |
| | | |
| | | funasr::Audio audio(1); |
| | | funasr::Audio audio(recog_obj->GetAsrSampleRate(),1); |
| | | if(wav_format == "pcm" || wav_format == "PCM"){ |
| | | if (!audio.LoadPcmwav(sz_buf, n_len, &sampling_rate)) |
| | | return nullptr; |
| | |
| | | if(p_result->snippet_time == 0){ |
| | | return p_result; |
| | | } |
| | | int n_step = 0; |
| | | int n_total = audio.GetQueueSize(); |
| | | |
| | | while (audio.Fetch(buff, len, flag) > 0) { |
| | | string msg = recog_obj->Forward(buff, len, input_finished); |
| | | p_result->msg += msg; |
| | | n_step++; |
| | | if (fn_callback) |
| | | fn_callback(n_step, n_total); |
| | | } |
| | | |
| | | return p_result; |
| | | } |
| | | |
| | |
| | | if (!recog_obj) |
| | | return nullptr; |
| | | |
| | | funasr::Audio audio(1); |
| | | funasr::Audio audio(recog_obj->GetAsrSampleRate(),1); |
| | | if(funasr::is_target_file(sz_filename, "wav")){ |
| | | int32_t sampling_rate_ = -1; |
| | | if(!audio.LoadWav(sz_filename, &sampling_rate_)) |
| | |
| | | float* buff; |
| | | int len; |
| | | int flag = 0; |
| | | int n_step = 0; |
| | | int n_total = audio.GetQueueSize(); |
| | | funasr::FUNASR_RECOG_RESULT* p_result = new funasr::FUNASR_RECOG_RESULT; |
| | | p_result->snippet_time = audio.GetTimeLen(); |
| | | if(p_result->snippet_time == 0){ |
| | |
| | | while (audio.Fetch(buff, len, flag) > 0) { |
| | | string msg = recog_obj->Forward(buff, len, true); |
| | | p_result->msg += msg; |
| | | n_step++; |
| | | if (fn_callback) |
| | | fn_callback(n_step, n_total); |
| | | } |
| | | |
| | | return p_result; |
| | | } |
| | | |
| | |
| | | if (!vad_obj) |
| | | return nullptr; |
| | | |
| | | funasr::Audio audio(1); |
| | | funasr::Audio audio(vad_obj->GetVadSampleRate(),1); |
| | | if(wav_format == "pcm" || wav_format == "PCM"){ |
| | | if (!audio.LoadPcmwav(sz_buf, n_len, &sampling_rate)) |
| | | return nullptr; |
| | |
| | | funasr::FUNASR_VAD_RESULT* p_result = new funasr::FUNASR_VAD_RESULT; |
| | | p_result->snippet_time = audio.GetTimeLen(); |
| | | if(p_result->snippet_time == 0){ |
| | | p_result->segments = new vector<std::vector<int>>(); |
| | | return p_result; |
| | | } |
| | | |
| | |
| | | if (!vad_obj) |
| | | return nullptr; |
| | | |
| | | funasr::Audio audio(1); |
| | | funasr::Audio audio(vad_obj->GetVadSampleRate(),1); |
| | | if(funasr::is_target_file(sz_filename, "wav")){ |
| | | int32_t sampling_rate_ = -1; |
| | | if(!audio.LoadWav(sz_filename, &sampling_rate_)) |
| | |
| | | funasr::FUNASR_VAD_RESULT* p_result = new funasr::FUNASR_VAD_RESULT; |
| | | p_result->snippet_time = audio.GetTimeLen(); |
| | | if(p_result->snippet_time == 0){ |
| | | p_result->segments = new vector<std::vector<int>>(); |
| | | return p_result; |
| | | } |
| | | |
| | |
| | | // APIs for Offline-stream Infer |
| | | _FUNASRAPI FUNASR_RESULT FunOfflineInferBuffer(FUNASR_HANDLE handle, const char* sz_buf, int n_len, |
| | | FUNASR_MODE mode, QM_CALLBACK fn_callback, const std::vector<std::vector<float>> &hw_emb, |
| | | int sampling_rate, std::string wav_format, bool itn, FUNASR_DEC_HANDLE dec_handle) |
| | | int sampling_rate, std::string wav_format, bool itn, FUNASR_DEC_HANDLE dec_handle, |
| | | std::string svs_lang, bool svs_itn) |
| | | { |
| | | funasr::OfflineStream* offline_stream = (funasr::OfflineStream*)handle; |
| | | if (!offline_stream) |
| | | return nullptr; |
| | | |
| | | funasr::Audio audio(1); |
| | | funasr::Audio audio(offline_stream->asr_handle->GetAsrSampleRate(),1); |
| | | try{ |
| | | if(wav_format == "pcm" || wav_format == "PCM"){ |
| | | if (!audio.LoadPcmwav(sz_buf, n_len, &sampling_rate)) |
| | |
| | | if(p_result->snippet_time == 0){ |
| | | return p_result; |
| | | } |
| | | std::vector<int> index_vector={0}; |
| | | int msg_idx = 0; |
| | | if(offline_stream->UseVad()){ |
| | | audio.Split(offline_stream); |
| | | audio.CutSplit(offline_stream, index_vector); |
| | | } |
| | | std::vector<string> msgs(index_vector.size()); |
| | | std::vector<float> msg_stimes(index_vector.size()); |
| | | |
| | | float* buff; |
| | | int len; |
| | | int flag = 0; |
| | | float** buff; |
| | | int* len; |
| | | int* flag; |
| | | float* start_time; |
| | | int batch_size = offline_stream->asr_handle->GetBatchSize(); |
| | | int batch_in = 0; |
| | | |
| | | int n_step = 0; |
| | | int n_total = audio.GetQueueSize(); |
| | | float start_time = 0.0; |
| | | std::string cur_stamp = "["; |
| | | std::string lang = (offline_stream->asr_handle)->GetLang(); |
| | | while (audio.Fetch(buff, len, flag, start_time) > 0) { |
| | | while (audio.FetchDynamic(buff, len, flag, start_time, batch_size, batch_in) > 0) { |
| | | // dec reset |
| | | funasr::WfstDecoder* wfst_decoder = (funasr::WfstDecoder*)dec_handle; |
| | | if (wfst_decoder){ |
| | | wfst_decoder->StartUtterance(); |
| | | } |
| | | string msg = (offline_stream->asr_handle)->Forward(buff, len, true, hw_emb, dec_handle); |
| | | std::vector<std::string> msg_vec = funasr::split(msg, '|'); |
| | | vector<string> msg_batch; |
| | | if(offline_stream->GetModelType() == MODEL_SVS){ |
| | | msg_batch = (offline_stream->asr_handle)->Forward(buff, len, true, svs_lang, svs_itn, batch_in); |
| | | }else{ |
| | | msg_batch = (offline_stream->asr_handle)->Forward(buff, len, true, hw_emb, dec_handle, batch_in); |
| | | } |
| | | for(int idx=0; idx<batch_in; idx++){ |
| | | string msg = msg_batch[idx]; |
| | | if(msg_idx < index_vector.size()){ |
| | | msgs[index_vector[msg_idx]] = msg; |
| | | msg_stimes[index_vector[msg_idx]] = start_time[idx]; |
| | | msg_idx++; |
| | | }else{ |
| | | LOG(ERROR) << "msg_idx: " << msg_idx <<" is out of range " << index_vector.size(); |
| | | } |
| | | } |
| | | |
| | | // release |
| | | delete[] buff; |
| | | buff = nullptr; |
| | | delete[] len; |
| | | len = nullptr; |
| | | delete[] flag; |
| | | flag = nullptr; |
| | | delete[] start_time; |
| | | start_time = nullptr; |
| | | } |
| | | for(int idx=0; idx<msgs.size(); idx++){ |
| | | string msg = msgs[idx]; |
| | | std::vector<std::string> msg_vec = funasr::SplitStr(msg, " | "); |
| | | if(msg_vec.size()==0){ |
| | | continue; |
| | | } |
| | |
| | | if(msg_vec.size() > 1){ |
| | | std::vector<std::string> msg_stamp = funasr::split(msg_vec[1], ','); |
| | | for(int i=0; i<msg_stamp.size()-1; i+=2){ |
| | | float begin = std::stof(msg_stamp[i])+start_time; |
| | | float end = std::stof(msg_stamp[i+1])+start_time; |
| | | float begin = std::stof(msg_stamp[i])+msg_stimes[idx]; |
| | | float end = std::stof(msg_stamp[i+1])+msg_stimes[idx]; |
| | | cur_stamp += "["+std::to_string((int)(1000*begin))+","+std::to_string((int)(1000*end))+"],"; |
| | | } |
| | | } |
| | | n_step++; |
| | | if (fn_callback) |
| | | fn_callback(n_step, n_total); |
| | | } |
| | | if(cur_stamp != "["){ |
| | | cur_stamp.erase(cur_stamp.length() - 1); |
| | |
| | | #if !defined(__APPLE__) |
| | | if(offline_stream->UseITN() && itn){ |
| | | string msg_itn = offline_stream->itn_handle->Normalize(p_result->msg); |
| | | if(!(p_result->stamp).empty()){ |
| | | std::string new_stamp = funasr::TimestampSmooth(p_result->msg, msg_itn, p_result->stamp); |
| | | if(!new_stamp.empty()){ |
| | | p_result->stamp = new_stamp; |
| | | } |
| | | } |
| | | p_result->msg = msg_itn; |
| | | } |
| | | #endif |
| | | |
| | | if (!(p_result->stamp).empty()){ |
| | | p_result->stamp_sents = funasr::TimestampSentence(p_result->msg, p_result->stamp); |
| | | } |
| | | return p_result; |
| | | } |
| | | |
| | |
| | | if (!offline_stream) |
| | | return nullptr; |
| | | |
| | | funasr::Audio audio(1); |
| | | funasr::Audio audio((offline_stream->asr_handle)->GetAsrSampleRate(),1); |
| | | try{ |
| | | if(funasr::is_target_file(sz_filename, "wav")){ |
| | | int32_t sampling_rate_ = -1; |
| | |
| | | if(p_result->snippet_time == 0){ |
| | | return p_result; |
| | | } |
| | | std::vector<int> index_vector={0}; |
| | | int msg_idx = 0; |
| | | if(offline_stream->UseVad()){ |
| | | audio.Split(offline_stream); |
| | | audio.CutSplit(offline_stream, index_vector); |
| | | } |
| | | std::vector<string> msgs(index_vector.size()); |
| | | std::vector<float> msg_stimes(index_vector.size()); |
| | | |
| | | float* buff; |
| | | int len; |
| | | int flag = 0; |
| | | int n_step = 0; |
| | | int n_total = audio.GetQueueSize(); |
| | | float start_time = 0.0; |
| | | float** buff; |
| | | int* len; |
| | | int* flag; |
| | | float* start_time; |
| | | int batch_size = offline_stream->asr_handle->GetBatchSize(); |
| | | int batch_in = 0; |
| | | |
| | | std::string cur_stamp = "["; |
| | | std::string lang = (offline_stream->asr_handle)->GetLang(); |
| | | while (audio.Fetch(buff, len, flag, start_time) > 0) { |
| | | while (audio.FetchDynamic(buff, len, flag, start_time, batch_size, batch_in) > 0) { |
| | | // dec reset |
| | | funasr::WfstDecoder* wfst_decoder = (funasr::WfstDecoder*)dec_handle; |
| | | if (wfst_decoder){ |
| | | wfst_decoder->StartUtterance(); |
| | | } |
| | | string msg = (offline_stream->asr_handle)->Forward(buff, len, true, hw_emb, dec_handle); |
| | | std::vector<std::string> msg_vec = funasr::split(msg, '|'); |
| | | vector<string> msg_batch = (offline_stream->asr_handle)->Forward(buff, len, true, hw_emb, dec_handle, batch_in); |
| | | for(int idx=0; idx<batch_in; idx++){ |
| | | string msg = msg_batch[idx]; |
| | | if(msg_idx < index_vector.size()){ |
| | | msgs[index_vector[msg_idx]] = msg; |
| | | msg_stimes[index_vector[msg_idx]] = start_time[idx]; |
| | | msg_idx++; |
| | | }else{ |
| | | LOG(ERROR) << "msg_idx: " << msg_idx <<" is out of range " << index_vector.size(); |
| | | } |
| | | } |
| | | |
| | | // release |
| | | delete[] buff; |
| | | buff = nullptr; |
| | | delete[] len; |
| | | len = nullptr; |
| | | delete[] flag; |
| | | flag = nullptr; |
| | | delete[] start_time; |
| | | start_time = nullptr; |
| | | } |
| | | for(int idx=0; idx<msgs.size(); idx++){ |
| | | string msg = msgs[idx]; |
| | | std::vector<std::string> msg_vec = funasr::SplitStr(msg, " | "); |
| | | if(msg_vec.size()==0){ |
| | | continue; |
| | | } |
| | |
| | | if(msg_vec.size() > 1){ |
| | | std::vector<std::string> msg_stamp = funasr::split(msg_vec[1], ','); |
| | | for(int i=0; i<msg_stamp.size()-1; i+=2){ |
| | | float begin = std::stof(msg_stamp[i])+start_time; |
| | | float end = std::stof(msg_stamp[i+1])+start_time; |
| | | float begin = std::stof(msg_stamp[i])+msg_stimes[idx]; |
| | | float end = std::stof(msg_stamp[i+1])+msg_stimes[idx]; |
| | | cur_stamp += "["+std::to_string((int)(1000*begin))+","+std::to_string((int)(1000*end))+"],"; |
| | | } |
| | | } |
| | | |
| | | n_step++; |
| | | if (fn_callback) |
| | | fn_callback(n_step, n_total); |
| | | } |
| | | if(cur_stamp != "["){ |
| | | cur_stamp.erase(cur_stamp.length() - 1); |
| | |
| | | #if !defined(__APPLE__) |
| | | if(offline_stream->UseITN() && itn){ |
| | | string msg_itn = offline_stream->itn_handle->Normalize(p_result->msg); |
| | | if(!(p_result->stamp).empty()){ |
| | | std::string new_stamp = funasr::TimestampSmooth(p_result->msg, msg_itn, p_result->stamp); |
| | | if(!new_stamp.empty()){ |
| | | p_result->stamp = new_stamp; |
| | | } |
| | | } |
| | | p_result->msg = msg_itn; |
| | | } |
| | | #endif |
| | | if (!(p_result->stamp).empty()){ |
| | | p_result->stamp_sents = funasr::TimestampSentence(p_result->msg, p_result->stamp); |
| | | } |
| | | return p_result; |
| | | } |
| | | |
| | | #if !defined(__APPLE__) |
| | | //#if !defined(__APPLE__) |
| | | _FUNASRAPI const std::vector<std::vector<float>> CompileHotwordEmbedding(FUNASR_HANDLE handle, std::string &hotwords, ASR_TYPE mode) |
| | | { |
| | | if (mode == ASR_OFFLINE){ |
| | |
| | | } |
| | | |
| | | } |
| | | #endif |
| | | //#endif |
| | | |
| | | // APIs for 2pass-stream Infer |
| | | _FUNASRAPI FUNASR_RESULT FunTpassInferBuffer(FUNASR_HANDLE handle, FUNASR_HANDLE online_handle, const char* sz_buf, |
| | | int n_len, std::vector<std::vector<std::string>> &punc_cache, bool input_finished, |
| | | int sampling_rate, std::string wav_format, ASR_TYPE mode, |
| | | const std::vector<std::vector<float>> &hw_emb, bool itn) |
| | | const std::vector<std::vector<float>> &hw_emb, bool itn, FUNASR_DEC_HANDLE dec_handle) |
| | | { |
| | | funasr::TpassStream* tpass_stream = (funasr::TpassStream*)handle; |
| | | funasr::TpassOnlineStream* tpass_online_stream = (funasr::TpassOnlineStream*)online_handle; |
| | |
| | | |
| | | audio->Split(vad_online_handle, chunk_len, input_finished, mode); |
| | | |
| | | funasr::AudioFrame* frame = NULL; |
| | | funasr::AudioFrame* frame = nullptr; |
| | | while(audio->FetchChunck(frame) > 0){ |
| | | string msg = ((funasr::ParaformerOnline*)asr_online_handle)->Forward(frame->data, frame->len, frame->is_final); |
| | | if(mode == ASR_ONLINE){ |
| | |
| | | }else if(mode == ASR_TWO_PASS){ |
| | | p_result->msg += msg; |
| | | } |
| | | if(frame != NULL){ |
| | | if(frame != nullptr){ |
| | | delete frame; |
| | | frame = NULL; |
| | | frame = nullptr; |
| | | } |
| | | } |
| | | |
| | | // timestamp |
| | | std::string cur_stamp = "["; |
| | | while(audio->FetchTpass(frame) > 0){ |
| | | string msg = ((funasr::Paraformer*)asr_handle)->Forward(frame->data, frame->len, frame->is_final, hw_emb); |
| | | |
| | | std::vector<std::string> msg_vec = funasr::split(msg, '|'); // split with timestamp |
| | | // dec reset |
| | | funasr::WfstDecoder* wfst_decoder = (funasr::WfstDecoder*)dec_handle; |
| | | if (wfst_decoder){ |
| | | wfst_decoder->StartUtterance(); |
| | | } |
| | | float** buff; |
| | | int* len; |
| | | buff = new float*[1]; |
| | | len = new int[1]; |
| | | buff[0] = frame->data; |
| | | len[0] = frame->len; |
| | | vector<string> msgs = ((funasr::Paraformer*)asr_handle)->Forward(buff, len, frame->is_final, hw_emb, dec_handle); |
| | | string msg = msgs.size()>0?msgs[0]:""; |
| | | std::vector<std::string> msg_vec = funasr::SplitStr(msg, " | "); // split with timestamp |
| | | if(msg_vec.size()==0){ |
| | | continue; |
| | | } |
| | |
| | | #if !defined(__APPLE__) |
| | | if(tpass_stream->UseITN() && itn){ |
| | | string msg_itn = tpass_stream->itn_handle->Normalize(msg_punc); |
| | | // TimestampSmooth |
| | | if(!(p_result->stamp).empty()){ |
| | | std::string new_stamp = funasr::TimestampSmooth(p_result->tpass_msg, msg_itn, p_result->stamp); |
| | | if(!new_stamp.empty()){ |
| | | p_result->stamp = new_stamp; |
| | | } |
| | | } |
| | | p_result->tpass_msg = msg_itn; |
| | | } |
| | | #endif |
| | | |
| | | if(frame != NULL){ |
| | | if (!(p_result->stamp).empty()){ |
| | | p_result->stamp_sents = funasr::TimestampSentence(p_result->tpass_msg, p_result->stamp); |
| | | } |
| | | if(frame != nullptr){ |
| | | delete frame; |
| | | frame = NULL; |
| | | frame = nullptr; |
| | | } |
| | | } |
| | | |
| | |
| | | return nullptr; |
| | | |
| | | return p_result->stamp.c_str(); |
| | | } |
| | | |
| | | _FUNASRAPI const char* FunASRGetStampSents(FUNASR_RESULT result) |
| | | { |
| | | funasr::FUNASR_RECOG_RESULT * p_result = (funasr::FUNASR_RECOG_RESULT*)result; |
| | | if(!p_result) |
| | | return nullptr; |
| | | |
| | | return p_result->stamp_sents.c_str(); |
| | | } |
| | | |
| | | _FUNASRAPI const char* FunASRGetTpassResult(FUNASR_RESULT result,int n_index) |
| | |
| | | funasr::WfstDecoder* mm = nullptr; |
| | | if (asr_type == ASR_OFFLINE) { |
| | | funasr::OfflineStream* offline_stream = (funasr::OfflineStream*)handle; |
| | | funasr::Paraformer* paraformer = (funasr::Paraformer*)offline_stream->asr_handle.get(); |
| | | if (paraformer->lm_) |
| | | mm = new funasr::WfstDecoder(paraformer->lm_.get(), |
| | | paraformer->GetPhoneSet(), paraformer->GetVocab(), glob_beam, lat_beam, am_scale); |
| | | auto paraformer = dynamic_cast<funasr::Paraformer*>(offline_stream->asr_handle.get()); |
| | | if(paraformer !=nullptr){ |
| | | if (paraformer->lm_){ |
| | | mm = new funasr::WfstDecoder(paraformer->lm_.get(), |
| | | paraformer->GetPhoneSet(), paraformer->GetLmVocab(), glob_beam, lat_beam, am_scale); |
| | | } |
| | | return mm; |
| | | } |
| | | #ifdef USE_GPU |
| | | auto paraformer_torch = dynamic_cast<funasr::ParaformerTorch*>(offline_stream->asr_handle.get()); |
| | | if(paraformer_torch !=nullptr){ |
| | | if (paraformer_torch->lm_){ |
| | | mm = new funasr::WfstDecoder(paraformer_torch->lm_.get(), |
| | | paraformer_torch->GetPhoneSet(), paraformer_torch->GetLmVocab(), glob_beam, lat_beam, am_scale); |
| | | } |
| | | return mm; |
| | | } |
| | | #endif |
| | | |
| | | } else if (asr_type == ASR_TWO_PASS){ |
| | | funasr::TpassStream* tpass_stream = (funasr::TpassStream*)handle; |
| | | auto paraformer = dynamic_cast<funasr::Paraformer*>(tpass_stream->asr_handle.get()); |
| | | if(paraformer !=nullptr){ |
| | | if (paraformer->lm_){ |
| | | mm = new funasr::WfstDecoder(paraformer->lm_.get(), |
| | | paraformer->GetPhoneSet(), paraformer->GetLmVocab(), glob_beam, lat_beam, am_scale); |
| | | } |
| | | return mm; |
| | | } |
| | | #ifdef USE_GPU |
| | | auto paraformer_torch = dynamic_cast<funasr::ParaformerTorch*>(tpass_stream->asr_handle.get()); |
| | | if(paraformer_torch !=nullptr){ |
| | | if (paraformer_torch->lm_){ |
| | | mm = new funasr::WfstDecoder(paraformer_torch->lm_.get(), |
| | | paraformer_torch->GetPhoneSet(), paraformer_torch->GetLmVocab(), glob_beam, lat_beam, am_scale); |
| | | } |
| | | return mm; |
| | | } |
| | | #endif |
| | | } |
| | | return mm; |
| | | } |