Kokoro-FastAPI
Kokoro-FastAPI copied to clipboard
remsky
Dockerized FastAPI wrapper for Kokoro-82M text-to-speech model w/CPU ONNX and NVIDIA GPU PyTorch support, handling, and auto-stitching
**Describe the feature you'd like** First of all, thanks for this very useful repo. I have variety of equipments and I would like to minimize use of discrete NVIDIA GPU...
**Describe the bug** When running the released image log is always DEBUG regardless of what the env var is set at. Noticed that [entrypoint.sh](https://github.com/remsky/Kokoro-FastAPI/blob/311ee6497b05dc904e505ba302048d08ba70c2ba/docker/scripts/entrypoint.sh#L8) forced debug log but trying to...
This PR will split up the Docker build targets by CPU and GPU and their various respective architectures. GitHub actions will now build all Docker targets in parallel and reducing...
The original code can support pure Chinese pronunciation very well, but when it comes to mixed Chinese and English pronunciation, the English pronunciation data will be lost. I have improved...
Made the CPU/GPU markers mutually exclusive (extra == 'cpu' and extra != 'gpu' / extra == 'gpu' and extra != 'cpu') to satisfy uv’s “disjoint markers” requirement and let uv...
**Describe the bug** The kokoro-fastapi-gpu images (latest and v0.2.4) both log `exec /opt/nvidia/nvidia_entrypoint.sh: exec format error` on launch and exit. There was a time when I was able to build...
The new pause handling is great. However, there seems to be a bug if a pause is placed as the first item in a sentence. If you put a single...
Fixes https://github.com/remsky/Kokoro-FastAPI/issues/308. In the end I didn't use ICU directly, since ICU support in Python can be a bit finnicky as a dependency and can't be added with a simple...
Add weighted voice blending support to combine endpoint This update introduces the ability to assign custom weights to each voice when generating a combined voice tensor. Previously, all voices were...
**Describe the bug** - Kokoro does not see the difference between shorts like "etc." in the middle and the end of the sentence. There is no pause at all after...
