Merge pull request #1130 from jamiepine/prep/pr-1112

Fix infinite HF retry storm when loading a cached model offline

backend/backends/chatterbox_turbo_backend.py

@@ -29,11 +29,19 @@ logger = logging.getLogger(__name__)
 
 CHATTERBOX_TURBO_HF_REPO = "ResembleAI/chatterbox-turbo"
 
-# Files that must be present for the turbo model
+# The files ChatterboxTurboTTS.from_local() reads, as of chatterbox-tts 0.1.7:
+# the three weight files, the GPT-2 tokenizer files AutoTokenizer needs, and
+# the built-in voice. The load runs with HF offline mode forced when this
+# reports cached, so a partial snapshot must not count as cached -- if upstream
+# starts reading another file, add it here too.
 _TURBO_WEIGHT_FILES = [
     "t3_turbo_v1.safetensors",
     "s3gen_meanflow.safetensors",
     "ve.safetensors",
+    "tokenizer_config.json",
+    "vocab.json",
+    "merges.txt",
+    "conds.pt",
 ]