Revert torch pin (broke spaces/ZeroGPU + Wan2.2/LTX-Video); make diarization best-effort and drop pyannote.audio dep. Transcription-only stays GPU-accelerated.

Pin torch/torchvision/torchaudio to 2.2.2 trio for pyannote 3.4.0 compat (reverts the AudioMetaData shim, which didn't find the class)

Shim torchaudio.AudioMetaData for pyannote 3.4.0 compat with newer torchaudio, without touching torch stack versions

Pin pyannote.audio==3.4.0 (newer versions redirect 3.1 pipeline to a different gated model)

Fix pyannote token kwarg (token= not use_auth_token=) and pin whisper language=en

Trigger fresh redeploy (previous restart reused stale build)

Fix: remove show_copy_button kwarg incompatible with this Space's Gradio version

Add audio transcription + speaker diarization tab (Whisper + pyannote)

Add Wan 2.2 pixel sprite animation endpoint

Upload studio/backends/hf_space.py with huggingface_hub

Upload requirements.txt with huggingface_hub

Upload app.py with huggingface_hub

add txt2img tab + infer_txt2img endpoint (SD 1.5)

add txt2img tab + infer_txt2img endpoint (SD 1.5)

Add peft + torchvision (required by diffusers load_lora_weights)

Initial venture-studio deploy: pixel_cursor + studio + app.py

initial commit

Duplicate from gradio-templates/text-to-image-gradio-template