Update Dockerfile

Dockerfile

@@ -1,4 +1,4 @@
-FROM python:3.12-slim
+FROM python:3.14-slim
 
 # Set environment variables for caching to a writable directory
 # These will be used by huggingface libraries to store models and other assets.
@@ -11,11 +11,15 @@ ENV HF_DATASETS_CACHE=/data/huggingface/datasets
 RUN mkdir -p $TRANSFORMERS_CACHE $HF_DATASETS_CACHE $TORCH_HOME && \
     chmod -R 777 /data
 
-# System deps for soundfile and audio encoding
+# System deps for soundfile, audio encoding, and uroman
 RUN apt-get update && apt-get install -y --no-install-recommends \
-    libsndfile1 ffmpeg git && \
+    libsndfile1 ffmpeg git 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
+
 WORKDIR /app
 
 # Install Python deps