Paul se #6
Open
Paul se #6
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
carloshmorales
requested changes
Jan 18, 2023
|
|
||
| #include <arm_math.h> | ||
|
|
||
| #define RUN_SPEED_TESTING 1 |
There was a problem hiding this comment.
do you want this enabled by default?
| .length = LEN_STFT_HOP * sizeof(int16_t), | ||
| .dType = uint8_e, | ||
| .description = msg_store, | ||
| .cmd = write_cmd, | ||
| .buffer = {.data = (uint8_t *) g_in16AudioDataBuffer, // point this to audio buffer | ||
| .dataLength = LEN_STFT_HOP * sizeof(int16_t)}}; | ||
| // Block sent to PC for computation | ||
| dataBlock computeBlock = { | ||
| dataBlock computeBlock = { // this block is useless here actually |
There was a problem hiding this comment.
There is an RPC call for this (but I just realized I don't have example code for it, will add): ns_rpc_data_fetchBlockFromPC(&block)
|
|
||
| #ifdef DEF_GUI_ENABLE | ||
| static char msg_store[30] = "Audio16bPCM_to_WAV"; | ||
| char msg_compute[30] = "CalculateMFCC_Please"; |
There was a problem hiding this comment.
This string can be anything you want, as long as it matches your python script.
| #endif | ||
| }; | ||
|
|
||
| const ns_power_config_t ns_lp_audio = { |
There was a problem hiding this comment.
Can delete this I think
|
|
||
| detected = NNSPClass_exec(pt_nnsp, pcmbuf_chunk); | ||
| for (int i = 0; i < SAMPLES_FRM_NNCNTRL_CLASS; i++) | ||
| se_output[i] = pt_nnsp->pt_se_out[i]; |
| for (i = 0; i < ps->hop; i++) | ||
| output[i] = (int16_t) MIN(MAX(ps->odataBuffer[i], INT16_MIN), INT16_MAX);; | ||
|
|
||
| for (i = 0; i < ps->len_win - ps->hop; i++) |
| } | ||
|
|
||
| pt_out = ps->odataBuffer + ps->len_win - ps->hop; | ||
| for (i = 0; i < ps->hop; i++) |
| spec_c = np.loadtxt('dump/file_feat_c', dtype=int) | ||
| fname = "file_feat" | ||
| spec_py = np.loadtxt(f'dump/{fname}_py', dtype=int) | ||
| spec_c = np.loadtxt(f'C:\\Users\\Paul Chen\\Documents\\nnsp_sol\\nnsp_simu\\dump\\{fname}_c', dtype=int) |
There was a problem hiding this comment.
Probably want a less personal file path :)
| */ | ||
| static int16_t pcmbuf_chunk[SAMPLES_FRM_NNCNTRL_CLASS]; | ||
| NNSPClass *pt_nnsp = (NNSPClass*) pt_inst->pt_nnsp; | ||
| int16_t detected = 0; |
There was a problem hiding this comment.
This is throwing a compile warning ("set but not used")
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
To run
SEon EVB, follow the steps below:From the
nnsp/evb/directory:make cleanmake NNSP_MODE=se GUI_ENABLE=1make deployPrepare two USB cables. Ensure your board is connected via both theJLINK USB portand theaudio USB port. Then turn on the power on EVB.make viewwill provide SWO output as the device is running, showingpredicted slots/intents etc.
recordto start recording andstopto stop recording.--ttydepending on your OS.nnsp/evb/audio_result/:audio_raw.wav: the raw PCM data recorded from your mic.audio_se.wav: the enhanced speech.