Update Dockerfile

Dockerfile

@@ -1,4 +1,13 @@
-FROM python:3.11-slim
+# Use a multi-stage build to handle uroman installation cleanly
+# ---- Builder Stage for uroman ----
+FROM python:3.10-slim as uroman-builder
+
+# Install uroman via pip in a temporary stage
+# This lets pip manage the download of the perl script
+RUN pip install uroman==1.3.1.1
+
+# ---- Final App Stage ----
+FROM python:3.10-slim
 
 # Set environment variables for caching to a writable directory
 # These will be used by huggingface libraries to store models and other assets.
@@ -13,12 +22,12 @@ RUN mkdir -p $TRANSFORMERS_CACHE $HF_DATASETS_CACHE $TORCH_HOME && \
 
 # System deps for soundfile, audio encoding, and uroman
 RUN apt-get update && apt-get install -y --no-install-recommends \
-    libsndfile1 ffmpeg git perl && \
+    libsndfile1 ffmpeg perl && \
     rm -rf /var/lib/apt/lists/*
 
-# Clone and install uroman from source so the tokenizer can find it
-RUN git clone https://github.com/isi-nlp/uroman.git /opt/uroman && \
-    ln -s /opt/uroman/bin/uroman.pl /usr/local/bin/uroman
+# Copy the uroman script from the builder stage and create the symlink
+COPY --from=uroman-builder /usr/local/lib/python3.10/site-packages/uroman/bin /opt/uroman
+RUN ln -s /opt/uroman/uroman.pl /usr/local/bin/uroman
 
 WORKDIR /app