Age | Commit message (Collapse) | Author | |
---|---|---|---|
2024-03-22 | use rnn_ prefix for non-exported symbolsupstream-master | Jean-Marc Valin | |
2024-03-22 | removing more symbols clash | Jean-Marc Valin | |
2024-03-22 | rename kiss-fft symbols | Jean-Marc Valin | |
2024-03-22 | Rename symbols to avoid clashes with Opus | Jean-Marc Valin | |
2021-03-12 | Add link to paper and demo to the README | Jean-Marc Valin | |
2021-01-22 | Correct #endif in rnn.h. | Petter Reinholdtsen | |
2021-01-22 | Document the API | Luca Barbato | |
2021-01-22 | Add rnnoise_get_frame_size() | Luca Barbato | |
It provides a mean to know how many samples are processed at time. | |||
2021-01-22 | Drop unused arguments from README (#103) | Danielius Visockas | |
Match wording given by usage. | |||
2021-01-18 | fix inclusion of rnnoise.h into C++ code | Johannes Schultz | |
2021-01-18 | Document in the README the authorative source for the code. | Petter Reinholdtsen | |
2021-01-18 | docs: fix simple typo, delares -> declares | Tim Gates | |
There is a small typo in src/kiss_fft.c. Should read `declares` rather than `delares`. | |||
2020-06-28 | rename TRAINING -> TRAINING-README for case insensitive file system | Peng Yu | |
2020-06-28 | Update celt_lpc.c | tangshi | |
2020-06-28 | Access files in binary mode | TimTim | |
2019-05-29 | Removing the long since broken non-SMOOTH_BANDS mode. | Gregor Richards | |
2019-05-29 | Adding instructions on training. | Gregor Richards | |
2019-05-29 | Updated README | Gregor Richards | |
2019-05-29 | Neural network model files | Gregor Richards | |
Extending the neural network dumper to dump to a simple text file format, and adding reader functions to read a neural network description from a FILE *. | |||
2019-05-29 | Made dump_rnn output in nu format. | Gregor Richards | |
2019-05-29 | Fix some warnings | Gregor Richards | |
2019-05-29 | Modularizing the RNN model | Gregor Richards | |
2017-10-17 | Limiting the gain decay | Jean-Marc Valin | |
2017-10-04 | Update README | Jan | |
Signed-off-by: Jean-Marc Valin <jmvalin@jmvalin.ca> | |||
2017-09-20 | Features #17 | Jean-Marc Valin | |
2017-09-17 | features #16 | Jean-Marc Valin | |
2017-09-15 | features #15 | Jean-Marc Valin | |
2017-09-15 | features #14 | Jean-Marc Valin | |
2017-09-15 | features #13 | Jean-Marc Valin | |
2017-09-14 | features #12 | Jean-Marc Valin | |
2017-09-13 | Output VAD prob | Jean-Marc Valin | |
2017-09-08 | Removing delay | Jean-Marc Valin | |
2017-09-08 | New features (#9) | Jean-Marc Valin | |
Also, adding an error^4 term to the loss function | |||
2017-09-02 | fix leak in example | Jean-Marc Valin | |
2017-09-01 | Cleanup | Jean-Marc Valin | |
2017-09-01 | Adding a real README | Jean-Marc Valin | |
2017-08-20 | don't need this file | Jean-Marc Valin | |
2017-08-20 | Retraining with features #8 (robust to low-passing) | Jean-Marc Valin | |
2017-08-18 | features #8 | Jean-Marc Valin | |
2017-08-18 | features #7 | Jean-Marc Valin | |
2017-08-18 | preventing extreme values | Jean-Marc Valin | |
2017-08-17 | Adding build system | Jean-Marc Valin | |
2017-08-16 | Adds pitch filtering | Jean-Marc Valin | |
2017-08-15 | minor refactoring | Jean-Marc Valin | |
2017-08-15 | split off analysis from features | Jean-Marc Valin | |
2017-08-15 | Wip (refactoring) | Jean-Marc Valin | |
2017-08-14 | still refactoring | Jean-Marc Valin | |
2017-08-14 | More refactoring | Jean-Marc Valin | |
2017-08-14 | Refactoring | Jean-Marc Valin | |
2017-08-14 | constraining the weights to +/- 0.5 so they can be quantized with 8 bits | Jean-Marc Valin | |