John | Elite Encoder
John | Elite Encoder
**Describe the bug** When operating an orchestrator with multiple remote transcoders, disconnecting one remote T can sometimes cause orchestrator to lose all transcoders and go into a `no transcoders available`...
**Describe the bug** There seems to be an issue with some segments arriving without necessary keyframe information, such as duration. When this happens, it is possible for a transcoder to...
**Is your feature request related to a problem? Please describe.** - A broadcaster sending a stream in AV1 encoding may not be able to use livepeer due to lack of...
**Is your feature request related to a problem? Please describe.** Remote transcoding tests might be flaky due to a `time.sleep` required with go-routines to connect remote T for testing. There...
**What does this pull request do? Explain your changes. (required)** This PR is dependent on https://github.com/livepeer/ai-worker/pull/79 The change checks if the requested model folder exists when loading during startup (warm...
**What does this pull request do? Explain your changes. (required)** Adds the new `/speech-to-text` pipeline to go-livepeer, supporting the `openai/whisper-large-v3` model. File formats supported are mp3, m4a, mp4, webm, wav...
**What does this pull request do? Explain your changes. (required)** Adds the ability to set preferred gpu by model in the aimodels config. ``` { "pipeline": "text-to-image", "model_id": "SG161222/RealVisXL_V4.0_Lightning", "price_per_unit":...
**What does this pull request do? Explain your changes. (required)** This change validates the ticket EV of an orchestrator to ensure it is sufficient for the prices that are set...
**What does this pull request do? Explain your changes. (required)** This change adds roundtrip time metrics for all pipelines, logging the specific pipeline, model and roundtrip time. You can visualize...
Add note about local user paths for python packages