-
Currently, transformers' [`FeaturesManager._TASKS_TO_AUTOMODELS`](https://github.com/huggingface/transformers/blob/6d80c92c77593dc674052b5a46431902e6adfe88/src/transformers/onnx/features.py#L103) to h…
-
### Bug description
When exporting as 8-bit unsigned, by default, Audacity applies dither, but the dither is (incorrectly) randomised between 0 and -1 bit. Consequently, it fails to prevent quantizat…
-
The _Paula_ is the sound chip on the _Amiga_ personal computer that produces audio from a 512KB bank of sample data. An existing project, [WinUAE](https://github.com/tonioni/WinUAE), emulates the Amig…
-
#### Introduction
Vector databases have gained significant importance due to the rise of AI, machine learning, and deep learning applications. These databases store high-dimensional vectors repre…
-
Achieving Faster Open-Source Llama3 Serving with SGLang Runtime (vs. TensorRT-LLM, vLLM)
https://lmsys.org/blog/2024-07-25-sglang-llama3/
gemma 2 update
https://huggingface.co/google/gemma-2-2b
…
-
### Describe the project you are working on
A first person shooter with a strong empasis on dynamic music.
### Describe the problem or limitation you are having in your project
Unlike most dy…
-
## Motivation #
There is significant interest in vLLM supporting encoder/decoder models. Issues #187 and #180 , for example, request encoder/decoder model support. As a result encoder/decoder supp…
-
Simple(ish) deformers (many from audio degradation toolbox):
- [ ] Low-, band-, high-pass filter
- [ ] bit-crushing
- [ ] companding+quantization noise
- should wait until https://github.com/li…
-
The docstrings of `mu_law_encoding` and `mu_law_decoding` say the following.
https://github.com/pytorch/audio/blob/a8fbbdac1de389cf7799b0abd0684f9b77c2f675/torchaudio/functional/functional.py#L491-…
-
I've created a "real-time" application with chunks of 3 sec using my own small fine-tuned model. It reads the complete audio call recording and generate 3s chunks, but in some cases I get repetition o…