ed3a91e4fa
This patch adds a perftest for the OONX speecht5-tts q8 quantized model as part of our ongoing exploration and benchmarking of TTS tasks for transform media type project. The goals are 1) add the first perftest for speech-to-text task as reference for future tests; 2) benchmark core performance metrics like latency and memory usage to assess realistic inference conditions (note that streaming audio output is not yet tested. This helps establish a baseline for comparing candidate TTS models (as well as different quantization levels) for future integration decisions. The test runs directly in transformers.js without any modification to the pipeline. Differential Revision: https://phabricator.services.mozilla.com/D248133
This directory contains common Python code. The basic rule is that if Python code is cross-module (that's "module" in the Mozilla meaning - as in "module ownership") and is MPL-compatible, it should go here. What should not go here: * Vendored python modules (use third_party/python instead) * Python that is not MPL-compatible (see other-licenses/) * Python that has good reason to remain close to its "owning" (Mozilla) module (e.g. it is only being consumed from there). Historical information can be found at https://bugzilla.mozilla.org/show_bug.cgi?id=775243 https://bugzilla.mozilla.org/show_bug.cgi?id=1346025