A Very Low-Bitrate Codec for Speech Compression
Lyra 1.3.2 is now available. Updating should be a medium priority for most users. This release is a relatively small change. It upgrades from TensorFlow 2.9 to the latest stable 2.11, which produces a ~10% speed improvement due to more modules being supported in XNNPack. The benchmark on the README is also updated to reflect the current bazel build, but note that previously it measured the internal build speed, which was already based on the faster TF 2.12.
Notes
Lyra 1.3.1 is now available. Updating should be a low priority for most users. This release contains mostly cosmetic changes due to a directory restructuring. However, for those who are considering submitting PRs, it would be helpful to sync to prevent merge conflicts.
Resolved Issues
Lyra 1.3.0 is now available. This release increases the speed and reduces the storage space of the model. We recommend all users upgrade if they do not need to reuse the earlier versions’ bitstream.
New Features
Breaking Changes
Lyra V2 (1.2.0) is now available. This release increases the quality and flexibility of the model. We recommend all users upgrade if they do not need to use the V1 bitstream.
New Features
.bazelrc
file. We welcome community contributions for this..tflite
files can be used in other platforms. The TFLite runtime is optimized for individual platforms, replacing the need to write platform specific assembly.Breaking Changes
set_bitrate()
API. Likewise, the bitrate parameter of the decoder was dropped, since it will decode each packet correctly, regardless of bitrate.DecodePacketLoss()
API was folded into DecodeSamples()
, which now switches to Packet Loss Concealment (PLC) when needed.lyra_encoder.h
API changes
set_bitrate()
Encode()
returns std::optional
instead of absl::optional
lyra_decoder.h
API changes
bitrate
as an argument to Create()
DecodePacketLoss()
DecodeSamples()
returns std::optional
instead of absl::optional
bitrate()
Lyra version 0.0.2 is now available on GitHub. The main improvement of this version is the open-source release of the sparse_matmul library code, which was co-developed by Google and DeepMind. That means no more pre-compiled “.so” dynamic library binaries and no more restrictions on which toolchain to use, which opens up the door to port Lyra onto different platforms. The full list of features and fixes include:
First release