Skip to content

Faster qwen3 tts #9

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
DhirenMhatre wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Faster qwen3 tts #9

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
51c26f1
feat(backends): add faster-qwen3-tts
mudler Feb 26, 2026
e169492
fix: this backend is CUDA only
mudler Feb 26, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
54 changes: 53 additions & 1 deletion .github/workflows/backend.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -210,6 +210,19 @@ jobs:
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-faster-qwen3-tts'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "faster-qwen3-tts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
Expand Down Expand Up @@ -575,6 +588,19 @@ jobs:
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-13-faster-qwen3-tts'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "faster-qwen3-tts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
Expand Down Expand Up @@ -705,6 +731,19 @@ jobs:
backend: "qwen-tts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
- build-type: 'l4t'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-cuda-13-arm64-faster-qwen3-tts'
runs-on: 'ubuntu-24.04-arm'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
ubuntu-version: '2404'
backend: "faster-qwen3-tts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
- build-type: 'l4t'
cuda-major-version: "13"
cuda-minor-version: "0"
Expand Down Expand Up @@ -1306,6 +1345,19 @@ jobs:
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2204'
- build-type: 'l4t'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-faster-qwen3-tts'
runs-on: 'ubuntu-24.04-arm'
base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
skip-drivers: 'true'
backend: "faster-qwen3-tts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2204'
- build-type: 'l4t'
cuda-major-version: "12"
cuda-minor-version: "0"
Expand Down Expand Up @@ -1905,7 +1957,7 @@ jobs:
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
platforms: 'linux/amd64,linux/arm64'
tag-latest: 'auto'
tag-suffix: '-cpu-voxcpm'
runs-on: 'ubuntu-latest'
Expand Down
8 changes: 6 additions & 2 deletions Makefile
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
# Disable parallel execution for backend builds
.NOTPARALLEL: backends/diffusers backends/llama-cpp backends/outetts backends/piper backends/stablediffusion-ggml backends/whisper backends/faster-whisper backends/silero-vad backends/local-store backends/huggingface backends/rfdetr backends/kitten-tts backends/kokoro backends/chatterbox backends/llama-cpp-darwin backends/neutts build-darwin-python-backend build-darwin-go-backend backends/mlx backends/diffuser-darwin backends/mlx-vlm backends/mlx-audio backends/stablediffusion-ggml-darwin backends/vllm backends/vllm-omni backends/moonshine backends/pocket-tts backends/qwen-tts backends/qwen-asr backends/nemo backends/voxcpm backends/whisperx backends/ace-step backends/voxtral
.NOTPARALLEL: backends/diffusers backends/llama-cpp backends/outetts backends/piper backends/stablediffusion-ggml backends/whisper backends/faster-whisper backends/silero-vad backends/local-store backends/huggingface backends/rfdetr backends/kitten-tts backends/kokoro backends/chatterbox backends/llama-cpp-darwin backends/neutts build-darwin-python-backend build-darwin-go-backend backends/mlx backends/diffuser-darwin backends/mlx-vlm backends/mlx-audio backends/stablediffusion-ggml-darwin backends/vllm backends/vllm-omni backends/moonshine backends/pocket-tts backends/qwen-tts backends/faster-qwen3-tts backends/qwen-asr backends/nemo backends/voxcpm backends/whisperx backends/ace-step backends/voxtral

GOCMD=go
GOTEST=$(GOCMD) test
Expand Down Expand Up @@ -317,6 +317,7 @@ prepare-test-extra: protogen-python
$(MAKE) -C backend/python/moonshine
$(MAKE) -C backend/python/pocket-tts
$(MAKE) -C backend/python/qwen-tts
$(MAKE) -C backend/python/faster-qwen3-tts
$(MAKE) -C backend/python/qwen-asr
$(MAKE) -C backend/python/nemo
$(MAKE) -C backend/python/voxcpm
Expand All @@ -334,6 +335,7 @@ test-extra: prepare-test-extra
$(MAKE) -C backend/python/moonshine test
$(MAKE) -C backend/python/pocket-tts test
$(MAKE) -C backend/python/qwen-tts test
$(MAKE) -C backend/python/faster-qwen3-tts test
$(MAKE) -C backend/python/qwen-asr test
$(MAKE) -C backend/python/nemo test
$(MAKE) -C backend/python/voxcpm test
Expand Down Expand Up @@ -473,6 +475,7 @@ BACKEND_VIBEVOICE = vibevoice|python|.|--progress=plain|true
BACKEND_MOONSHINE = moonshine|python|.|false|true
BACKEND_POCKET_TTS = pocket-tts|python|.|false|true
BACKEND_QWEN_TTS = qwen-tts|python|.|false|true
BACKEND_FASTER_QWEN3_TTS = faster-qwen3-tts|python|.|false|true
BACKEND_QWEN_ASR = qwen-asr|python|.|false|true
BACKEND_NEMO = nemo|python|.|false|true
BACKEND_VOXCPM = voxcpm|python|.|false|true
Expand Down Expand Up @@ -525,6 +528,7 @@ $(eval $(call generate-docker-build-target,$(BACKEND_VIBEVOICE)))
$(eval $(call generate-docker-build-target,$(BACKEND_MOONSHINE)))
$(eval $(call generate-docker-build-target,$(BACKEND_POCKET_TTS)))
$(eval $(call generate-docker-build-target,$(BACKEND_QWEN_TTS)))
$(eval $(call generate-docker-build-target,$(BACKEND_FASTER_QWEN3_TTS)))
$(eval $(call generate-docker-build-target,$(BACKEND_QWEN_ASR)))
$(eval $(call generate-docker-build-target,$(BACKEND_NEMO)))
$(eval $(call generate-docker-build-target,$(BACKEND_VOXCPM)))
Expand All @@ -535,7 +539,7 @@ $(eval $(call generate-docker-build-target,$(BACKEND_ACE_STEP)))
docker-save-%: backend-images
docker save local-ai-backend:$* -o backend-images/$*.tar

docker-build-backends: docker-build-llama-cpp docker-build-rerankers docker-build-vllm docker-build-vllm-omni docker-build-transformers docker-build-outetts docker-build-diffusers docker-build-kokoro docker-build-faster-whisper docker-build-coqui docker-build-chatterbox docker-build-vibevoice docker-build-moonshine docker-build-pocket-tts docker-build-qwen-tts docker-build-qwen-asr docker-build-nemo docker-build-voxcpm docker-build-whisperx docker-build-ace-step docker-build-voxtral
docker-build-backends: docker-build-llama-cpp docker-build-rerankers docker-build-vllm docker-build-vllm-omni docker-build-transformers docker-build-outetts docker-build-diffusers docker-build-kokoro docker-build-faster-whisper docker-build-coqui docker-build-chatterbox docker-build-vibevoice docker-build-moonshine docker-build-pocket-tts docker-build-qwen-tts docker-build-faster-qwen3-tts docker-build-qwen-asr docker-build-nemo docker-build-voxcpm docker-build-whisperx docker-build-ace-step docker-build-voxtral

########################################################
### Mock Backend for E2E Tests
Expand Down
73 changes: 73 additions & 0 deletions backend/index.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -528,6 +528,28 @@
nvidia-l4t-cuda-12: "nvidia-l4t-qwen-tts"
nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-qwen-tts"
icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png
- &faster-qwen3-tts
urls:
- https://github.com/andimarafioti/faster-qwen3-tts
- https://pypi.org/project/faster-qwen3-tts/
description: |
Real-time Qwen3-TTS inference using CUDA graph capture. Voice clone only; requires NVIDIA GPU with CUDA.
tags:
- text-to-speech
- TTS
- voice-clone
license: apache-2.0
name: "faster-qwen3-tts"
alias: "faster-qwen3-tts"
capabilities:
nvidia: "cuda12-faster-qwen3-tts"
default: "cuda12-faster-qwen3-tts"
nvidia-cuda-13: "cuda13-faster-qwen3-tts"
Comment on lines +544 to +547

@codity-ai codity-ai Bot May 21, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Functional High

Selecting the new backend with capability default on a CPU-only host now resolves to cuda12-faster-qwen3-tts, so a request like backend: faster-qwen3-tts without NVIDIA hardware will always pull a CUDA image and fail at runtime because backend.py rejects torch.cuda.is_available()==False.

Remove the default capability for this backend or point it to no image/CPU-safe fallback so generic backend selection does not choose a CUDA-only container on non-NVIDIA machines.

Prompt for AI assistance

Copy the prompt below and paste it into ChatGPT, Claude, or any LLM:

You are an expert yaml developer with deep knowledge of security, performance, and best practices.

### Context

File: backend/index.yaml
Lines: 544-547
Issue Type: functional-high
Severity: high

Issue Description:
Selecting the new backend with capability `default` on a CPU-only host now resolves to `cuda12-faster-qwen3-tts`, so a request like `backend: faster-qwen3-tts` without NVIDIA hardware will always pull a CUDA image and fail at runtime because `backend.py` rejects `torch.cuda.is_available()==False`.

Current Code:
  capabilities:
    nvidia: "cuda12-faster-qwen3-tts"
    default: "cuda12-faster-qwen3-tts"
    nvidia-cuda-13: "cuda13-faster-qwen3-tts"
    nvidia-cuda-12: "cuda12-faster-qwen3-tts"

---

### Instructions

1. Fix the issue described above
2. Maintain the exact indentation and code style from the original
3. Follow yaml best practices and language-specific idioms
4. Ensure the fix addresses the root cause, not just the symptoms
5. Add brief inline comments explaining the fix if needed

### Constraints

- Do not change functionality beyond fixing the identified issue
- Preserve existing variable names and function signatures unless they are part of the problem
- Ensure the fix is production-ready

---

Like Dislike Create Issue

nvidia-cuda-12: "cuda12-faster-qwen3-tts"
nvidia-l4t: "nvidia-l4t-faster-qwen3-tts"
nvidia-l4t-cuda-12: "nvidia-l4t-faster-qwen3-tts"
nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-faster-qwen3-tts"
icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png
- &qwen-asr
urls:
- https://github.com/QwenLM/Qwen3-ASR
Expand Down Expand Up @@ -2279,6 +2301,57 @@
uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-qwen-tts"
mirrors:
- localai/localai-backends:master-metal-darwin-arm64-qwen-tts
## faster-qwen3-tts
- !!merge <<: *faster-qwen3-tts
Comment on lines 2301 to +2305

@codity-chait codity-chait Bot Jun 3, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Functional Medium

The faster-qwen3-tts-development entry (the first merged block after the anchor) overrides capabilities but does NOT set a uri or mirrors. This means the development variant has no image URI; when LocalAI tries to resolve and pull this backend image for a development/master install, it will find no image reference and fail silently or with a confusing error. The qwen-tts-development entry and others in the file all carry explicit uri + mirrors pointing to master-* tagged images.

Suggested fix 
- !!merge <<: *faster-qwen3-tts
  name: "faster-qwen3-tts-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-faster-qwen3-tts"
  mirrors:
    - localai/localai-backends:master-gpu-nvidia-cuda-12-faster-qwen3-tts
  capabilities:
    nvidia: "cuda12-faster-qwen3-tts-development"
    default: "cuda12-faster-qwen3-tts-development"
    nvidia-cuda-13: "cuda13-faster-qwen3-tts-development"
    nvidia-cuda-12: "cuda12-faster-qwen3-tts-development"
    nvidia-l4t: "nvidia-l4t-faster-qwen3-tts-development"
    nvidia-l4t-cuda-12: "nvidia-l4t-faster-qwen3-tts-development"
    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-faster-qwen3-tts-development"
Prompt for AI assistance

Copy the prompt below and paste it into ChatGPT, Claude, or any LLM:

You are an expert bash developer with deep knowledge of security, performance, and best practices.

### Context

File: backend/index.yaml
Lines: 2301-2305
Issue Type: functional-medium
Severity: medium

Issue Description:
The `faster-qwen3-tts-development` entry (the first merged block after the anchor) overrides `capabilities` but does NOT set a `uri` or `mirrors`. This means the development variant has no image URI; when LocalAI tries to resolve and pull this backend image for a development/master install, it will find no image reference and fail silently or with a confusing error. The `qwen-tts-development` entry and others in the file all carry explicit `uri` + `mirrors` pointing to `master-*` tagged images.

Current Code:
- !!merge <<: *faster-qwen3-tts
  name: "faster-qwen3-tts-development"
  capabilities:
    nvidia: "cuda12-faster-qwen3-tts-development"
    default: "cuda12-faster-qwen3-tts-development"
    nvidia-cuda-13: "cuda13-faster-qwen3-tts-development"
    nvidia-cuda-12: "cuda12-faster-qwen3-tts-development"
    nvidia-l4t: "nvidia-l4t-faster-qwen3-tts-development"
    nvidia-l4t-cuda-12: "nvidia-l4t-faster-qwen3-tts-development"
    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-faster-qwen3-tts-development"

---

### Instructions

1. Fix the issue described above
2. Maintain the exact indentation and code style from the original
3. Follow bash best practices and language-specific idioms
4. Ensure the fix addresses the root cause, not just the symptoms
5. Add brief inline comments explaining the fix if needed

### Constraints

- Do not change functionality beyond fixing the identified issue
- Preserve existing variable names and function signatures unless they are part of the problem
- Ensure the fix is production-ready

---

Like Dislike Create Issue

name: "faster-qwen3-tts-development"
capabilities:
nvidia: "cuda12-faster-qwen3-tts-development"
default: "cuda12-faster-qwen3-tts-development"
nvidia-cuda-13: "cuda13-faster-qwen3-tts-development"
nvidia-cuda-12: "cuda12-faster-qwen3-tts-development"
nvidia-l4t: "nvidia-l4t-faster-qwen3-tts-development"
nvidia-l4t-cuda-12: "nvidia-l4t-faster-qwen3-tts-development"
nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-faster-qwen3-tts-development"
- !!merge <<: *faster-qwen3-tts
name: "cuda12-faster-qwen3-tts"
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-faster-qwen3-tts"
mirrors:
- localai/localai-backends:latest-gpu-nvidia-cuda-12-faster-qwen3-tts
- !!merge <<: *faster-qwen3-tts
name: "cuda12-faster-qwen3-tts-development"
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-faster-qwen3-tts"
mirrors:
- localai/localai-backends:master-gpu-nvidia-cuda-12-faster-qwen3-tts
- !!merge <<: *faster-qwen3-tts
name: "cuda13-faster-qwen3-tts"
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-faster-qwen3-tts"
mirrors:
- localai/localai-backends:latest-gpu-nvidia-cuda-13-faster-qwen3-tts
- !!merge <<: *faster-qwen3-tts
name: "cuda13-faster-qwen3-tts-development"
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-faster-qwen3-tts"
mirrors:
- localai/localai-backends:master-gpu-nvidia-cuda-13-faster-qwen3-tts
- !!merge <<: *faster-qwen3-tts
name: "nvidia-l4t-faster-qwen3-tts"
uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-faster-qwen3-tts"
mirrors:
- localai/localai-backends:latest-nvidia-l4t-faster-qwen3-tts
- !!merge <<: *faster-qwen3-tts
name: "nvidia-l4t-faster-qwen3-tts-development"
uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-faster-qwen3-tts"
mirrors:
- localai/localai-backends:master-nvidia-l4t-faster-qwen3-tts
- !!merge <<: *faster-qwen3-tts
name: "cuda13-nvidia-l4t-arm64-faster-qwen3-tts"
uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-faster-qwen3-tts"
mirrors:
- localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-faster-qwen3-tts
- !!merge <<: *faster-qwen3-tts
name: "cuda13-nvidia-l4t-arm64-faster-qwen3-tts-development"
uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-faster-qwen3-tts"
mirrors:
- localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-faster-qwen3-tts
## qwen-asr
- !!merge <<: *qwen-asr
name: "qwen-asr-development"
Expand Down
23 changes: 23 additions & 0 deletions backend/python/faster-qwen3-tts/Makefile
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,23 @@
.PHONY: faster-qwen3-tts
faster-qwen3-tts:
bash install.sh

.PHONY: run
run: faster-qwen3-tts
@echo "Running faster-qwen3-tts..."
bash run.sh
@echo "faster-qwen3-tts run."

.PHONY: test
test: faster-qwen3-tts
@echo "Testing faster-qwen3-tts..."
bash test.sh
@echo "faster-qwen3-tts tested."

.PHONY: protogen-clean
protogen-clean:
$(RM) backend_pb2_grpc.py backend_pb2.py

.PHONY: clean
clean: protogen-clean
rm -rf venv __pycache__
Loading