1 /* Copyright (c) 2023 Amazon */ 2 /* 3 Redistribution and use in source and binary forms, with or without 4 modification, are permitted provided that the following conditions 5 are met: 6 7 - Redistributions of source code must retain the above copyright 8 notice, this list of conditions and the following disclaimer. 9 10 - Redistributions in binary form must reproduce the above copyright 11 notice, this list of conditions and the following disclaimer in the 12 documentation and/or other materials provided with the distribution. 13 14 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 15 ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT 16 LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR 17 A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER 18 OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, 19 EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, 20 PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR 21 PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF 22 LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING 23 NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS 24 SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 25 */ 26 27 #ifndef FARGAN_H 28 #define FARGAN_H 29 30 #include "freq.h" 31 #include "fargan_data.h" 32 #include "pitchdnn.h" 33 34 #define FARGAN_CONT_SAMPLES 320 35 #define FARGAN_NB_SUBFRAMES 4 36 #define FARGAN_SUBFRAME_SIZE 40 37 #define FARGAN_FRAME_SIZE (FARGAN_NB_SUBFRAMES*FARGAN_SUBFRAME_SIZE) 38 #define FARGAN_COND_SIZE (COND_NET_FDENSE2_OUT_SIZE/FARGAN_NB_SUBFRAMES) 39 #define FARGAN_DEEMPHASIS 0.85f 40 41 #define SIG_NET_INPUT_SIZE (FARGAN_COND_SIZE+2*FARGAN_SUBFRAME_SIZE+4) 42 #define SIG_NET_FWC0_STATE_SIZE (2*SIG_NET_INPUT_SIZE) 43 44 #define FARGAN_MAX_RNN_NEURONS SIG_NET_GRU1_OUT_SIZE 45 typedef struct { 46 FARGAN model; 47 int arch; 48 int cont_initialized; 49 float deemph_mem; 50 float pitch_buf[PITCH_MAX_PERIOD]; 51 float cond_conv1_state[COND_NET_FCONV1_STATE_SIZE]; 52 float fwc0_mem[SIG_NET_FWC0_STATE_SIZE]; 53 float gru1_state[SIG_NET_GRU1_STATE_SIZE]; 54 float gru2_state[SIG_NET_GRU2_STATE_SIZE]; 55 float gru3_state[SIG_NET_GRU3_STATE_SIZE]; 56 int last_period; 57 } FARGANState; 58 59 void fargan_init(FARGANState *st); 60 int fargan_load_model(FARGANState *st, const void *data, int len); 61 62 void fargan_cont(FARGANState *st, const float *pcm0, const float *features0); 63 64 void fargan_synthesize(FARGANState *st, float *pcm, const float *features); 65 void fargan_synthesize_int(FARGANState *st, opus_int16 *pcm, const float *features); 66 67 68 #endif /* FARGAN_H */ 69