Labyricorn/voicebox
1
0
Fork 0
mirror of https://github.com/jamiepine/voicebox.git synced 2026-10-03 09:05:17 -07:00
Code Issues Packages Projects Releases Wiki Activity

Update release workflow and model references

Browse Source 
- Added a step to install PyTorch with CUDA for Windows in the release workflow.
- Updated model references in backend/main.py to use openai/whisper models instead of mlx-community for the MLX backend.
This commit is contained in:
Jamie Pine
2026-01-30 18:10:17 -08:00
parent 46f6806e14
commit 77418a52ae
2 changed files with 11 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/release.yml
+6
View File
@@ -66,6 +66,12 @@ jobs:
run: | run: |
pip install -r backend/requirements-mlx.txt pip install -r backend/requirements-mlx.txt
- name: Install PyTorch with CUDA (Windows only)
if: matrix.platform == 'windows-latest'
run: |
pip install torch --index-url https://download.pytorch.org/whl/cu121 --force-reinstall --no-deps
pip install torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121
- name: Build Python server (Linux/macOS) - name: Build Python server (Linux/macOS)
if: matrix.platform != 'windows-latest' if: matrix.platform != 'windows-latest'
run: | run: |
backend/main.py
+5 -4
View File
@@ -1189,10 +1189,11 @@ async def get_model_status():
if backend_type == "mlx": if backend_type == "mlx":
tts_1_7b_id = "mlx-community/Qwen3-TTS-12Hz-1.7B-Base-bf16" tts_1_7b_id = "mlx-community/Qwen3-TTS-12Hz-1.7B-Base-bf16"
tts_0_6b_id = "mlx-community/Qwen3-TTS-12Hz-1.7B-Base-bf16" # Fallback to 1.7B tts_0_6b_id = "mlx-community/Qwen3-TTS-12Hz-1.7B-Base-bf16" # Fallback to 1.7B
whisper_base_id = "mlx-community/whisper-base" # MLX backend uses openai/whisper-* models, not mlx-community
whisper_small_id = "mlx-community/whisper-small" whisper_base_id = "openai/whisper-base"
whisper_medium_id = "mlx-community/whisper-medium" whisper_small_id = "openai/whisper-small"
whisper_large_id = "mlx-community/whisper-large" whisper_medium_id = "openai/whisper-medium"
whisper_large_id = "openai/whisper-large"
else: else:
tts_1_7b_id = "Qwen/Qwen3-TTS-12Hz-1.7B-Base" tts_1_7b_id = "Qwen/Qwen3-TTS-12Hz-1.7B-Base"
tts_0_6b_id = "Qwen/Qwen3-TTS-12Hz-0.6B-Base" tts_0_6b_id = "Qwen/Qwen3-TTS-12Hz-0.6B-Base"