Update app.py

app.py

@@ -231,12 +231,12 @@ class Translators:
         from quickmt import Translator
         # 'auto' auto-detects GPU, set to "cpu" to force CPU inference
         # device = 'gpu' if torch.cuda.is_available() else 'cpu'
-        translator = Translator(str(model_path))       
+        translator = Translator(str(model_path), device="auto", compute_type="auto", beam_size=5, max_input_length = 512, max_decoding_length = 512)       
         # translation = Translator(f"./quickmt-{self.sl}-{self.tl}/", device="auto/cpu", intra_threads=2, inter_threads=2, compute_type="int8")       
         # set beam size to 1 for faster speed (but lower quality) device="auto/cpu/gpu"
         # Options for compute_type: default, auto, int8, int8_float32, int8_float16, int8_bfloat16, int16, float16, bfloat16, float32
         # "int8" will work well for inference on CPU and give "int8_float16" or "int8_bfloat16" a try for GPU inference.
-        translation = translator(input_text, device="auto", compute_type="auto", beam_size=5, max_input_length = 512, max_decoding_length = 512)
+        translation = translator(input_text)
         # print(model_path, input_text, translation)
         return translation