fixes.

.gitattributes

@@ -1,35 +0,0 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -16,7 +16,5 @@ RUN pip install --upgrade pip && pip install -r requirements.txt
 
 COPY app.py ./
 
-# Default port for Spaces
 ENV PORT=7860
-
 CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -1,6 +1,6 @@
 ---
 title: xtts-v2-api
-emoji: 🗣️
+emoji: "🗣️"
 colorFrom: purple
 colorTo: blue
 sdk: docker
@@ -20,11 +20,16 @@ FastAPI service exposing XTTS v2 for text-to-speech and voice cloning.
 Send header `x-api-key: $SPACE_API_KEY` (set this secret in Space settings).
 
 ## Request body (`/generate`)
+```json
 {
   "text": "Hello from XTTS",
   "speaker_wav": "https://.../sample.wav or base64 string",
   "language": "en"
-}## Smoke tests
+}
+```
+
+## Smoke tests
+```bash
 curl -X POST https://<space>.hf.space/health \
   -H "x-api-key: $SPACE_API_KEY"
 
@@ -32,6 +37,9 @@ curl -X POST https://<space>.hf.space/generate \
   -H "Content-Type: application/json" \
   -H "x-api-key: $SPACE_API_KEY" \
   -d '{"text":"Hello from XTTS","speaker_wav":"https://.../sample.wav"}' \
-  --output out.wav## Notes
+  --output out.wav
+```
+
+## Notes
 - Hardware: request T4 GPU for best latency (CPU works but slower).
-- Env vars for clients: `HF_SPACES_API_URL`, `HF_SPACES_API_KEY`.
+- Env vars for clients: `HF_SPACES_API_URL`, `HF_SPACES_API_KEY`.

app.py

@@ -16,15 +16,11 @@ SPACE_API_KEY = os.getenv("SPACE_API_KEY")
 MAX_TEXT_LENGTH = 1000
 DEFAULT_LANGUAGE = "en"
 
-# Pick CUDA if available
 DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
 
-# Load the XTTS v2 model once at startup
-# Hugging Face Spaces caches model weights on persistent storage
 try:
     tts_model = TTS("tts_models/multilingual/multi-dataset/xtts_v2", gpu=DEVICE == "cuda")
-except Exception as exc:  # pragma: no cover - startup failure path
-    # Fail fast on startup; Spaces will show the error in logs
+except Exception as exc:  # pragma: no cover
     raise RuntimeError(f"Failed to load XTTS v2 model: {exc}") from exc
 
 app = FastAPI(title="xtts-v2-api", version="1.0.0")
@@ -32,8 +28,8 @@ app = FastAPI(title="xtts-v2-api", version="1.0.0")
 
 class GenerateRequest(BaseModel):
     text: str = Field(..., min_length=1, max_length=MAX_TEXT_LENGTH)
-    speaker_wav: str = Field(..., description="HTTPS URL or base64-encoded WAV/MP3/M4A")
-    language: Optional[str] = Field(DEFAULT_LANGUAGE, description="ISO language code, default en")
+    speaker_wav: str = Field(..., description="HTTPS URL or base64-encoded audio")
+    language: Optional[str] = Field(DEFAULT_LANGUAGE, description="ISO code, default en")
 
 
 def _require_api_key(x_api_key: Optional[str]):
@@ -58,7 +54,7 @@ def _write_temp_audio_from_url(url: HttpUrl) -> str:
 def _write_temp_audio_from_base64(payload: str) -> str:
     try:
         raw = base64.b64decode(payload)
-    except Exception as exc:  # pragma: no cover - malformed base64
+    except Exception as exc:  # pragma: no cover
         raise HTTPException(status_code=400, detail="Invalid base64 speaker_wav") from exc
     with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as tmp:
         tmp.write(raw)
@@ -104,8 +100,7 @@ def generate(
 
     except HTTPException:
         raise
-    except Exception as exc:  # pragma: no cover - runtime failure path
-        # Surface readable errors to client
+    except Exception as exc:  # pragma: no cover
         return JSONResponse(status_code=500, content={"error": str(exc)})
     finally:
         if speaker_file and Path(speaker_file).exists():

requirements.txt

@@ -1,8 +1,10 @@
 TTS==0.22.0
 fastapi==0.104.1
 uvicorn==0.24.0
-torch==2.1.0
-torchaudio==2.1.0
 python-multipart==0.0.6
 requests==2.31.0
 numpy==1.26.4
+
+# Use CPU wheels by default; HF GPU image will still use CUDA when available.
+torch==2.1.0 --index-url https://download.pytorch.org/whl/cpu
+torchaudio==2.1.0 --index-url https://download.pytorch.org/whl/cpu

spaces.yaml

@@ -1,5 +1,4 @@
 title: xtts-v2-api
 sdk: docker
-dockerfile: Dockerfile
 python_version: 3.10
 app_file: app.py