Quickmt auto changes

app.py

@@ -230,11 +230,13 @@ class Translators:
     def quickmttranslate(model_path, input_text):
         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), device = device)       
-        # translation = Translator(f"./quickmt-{self.sl}-{self.tl}/", device="auto", inter_threads=2)       
-        # set beam size to 1 for faster speed (but lower quality)
-        translation = translator(input_text, beam_size=5, max_input_length = 512, max_decoding_length = 512)
+        # device = 'gpu' if torch.cuda.is_available() else 'cpu'
+        translator = Translator(str(model_path))       
+        # 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)
         # print(model_path, input_text, translation)
         return translation
 
@@ -257,15 +259,15 @@ class Translators:
         # quickmt_models.sort()
         quickmt_models = ['ar-en', 'bn-en', 'cs-en', 'da-en', 'de-en', 'el-en', 'en-ar', 'en-bn',
                           'en-cs', 'en-da', 'en-de', 'en-el', 'en-es', 'en-fa', 'en-fr', 'en-he',
-                          'en-hi', 'en-hu', 'en-id', 'en-it', 'en-ja', 'en-ko', 'en-lv', 'en-pl',
+                          'en-hi', 'en-hu', 'en-id', 'en-is', 'en-it', 'en-ja', 'en-ko', 'en-lv', 'en-pl',
                           'en-pt', 'en-ro', 'en-ru', 'en-sv', 'en-th', 'en-tr', 'en-ur', 'en-vi',
                           'en-zh', 'es-en', 'fa-en', 'fr-en', 'he-en', 'hi-en', 'hu-en', 'id-en',
-                          'it-en', 'ja-en', 'ko-en', 'lv-en', 'pl-en', 'pt-en', 'ro-en', 'ru-en',
+                          'is-en', 'it-en', 'ja-en', 'ko-en', 'lv-en', 'pl-en', 'pt-en', 'ro-en', 'ru-en',
                           'th-en', 'tr-en', 'ur-en', 'vi-en', 'zh-en']
         # available_languages = list(set([lang for model in quickmt_models for lang in model.split('-')]))
         # available_languages.sort()
         available_languages = ['ar', 'bn', 'cs', 'da', 'de', 'el', 'en', 'es', 'fa', 'fr', 'he',
-                               'hi', 'hu', 'id', 'it', 'ja', 'ko', 'lv', 'pl', 'pt', 'ro', 'ru',
+                               'hi', 'hu', 'id', 'it', 'is', 'ja', 'ko', 'lv', 'pl', 'pt', 'ro', 'ru',
                                'sv', 'th', 'tr', 'ur', 'vi', 'zh']
         # print(quickmt_models, available_languages)       
         # Direct translation model
@@ -707,13 +709,9 @@ def get_info(model_name: str, sl: str = None, tl: str = None):
             'is-en', 'mt-en', 'nn-en', 'sq-en', 'sw-en', 'zh_hant-en']"""
     elif "QUICKMT" in model_name:
         return """[QUICKMT](https://huggingface.co/quickmt)  
-            ['ar-en', 'bn-en', 'cs-en', 'da-en', 'de-en', 'el-en', 'en-ar', 'en-bn',
-              'en-cs', 'en-da', 'en-de', 'en-el', 'en-es', 'en-fa', 'en-fr', 'en-he',
-              'en-hi', 'en-hu', 'en-id', 'en-it', 'en-ja', 'en-ko', 'en-lv', 'en-pl',
-              'en-pt', 'en-ro', 'en-ru', 'en-sv', 'en-th', 'en-tr', 'en-ur', 'en-vi',
-              'en-zh', 'es-en', 'fa-en', 'fr-en', 'he-en', 'hi-en', 'hu-en', 'id-en',
-              'it-en', 'ja-en', 'ko-en', 'lv-en', 'pl-en', 'pt-en', 'ro-en', 'ru-en',
-              'th-en', 'tr-en', 'ur-en', 'vi-en', 'zh-en']"""
+            ['ar', 'bn', 'cs', 'da', 'de', 'el', 'en', 'es', 'fa', 'fr', 'he',
+           'hi', 'hu', 'id', 'it', 'is', 'ja', 'ko', 'lv', 'pl', 'pt', 'ro', 'ru',
+           'sv', 'th', 'tr', 'ur', 'vi', 'zh']"""
     elif model_name == "Google":
         return "Google Translate Online"
     else:
@@ -721,8 +719,8 @@ def get_info(model_name: str, sl: str = None, tl: str = None):
 
 with gr.Blocks() as interface:
     gr.Markdown("### Machine Text Translation with Gradio API and MCP Server")
-    input_text = gr.Textbox(label="Enter text to translate:", placeholder="Type your text here, maximum 512 tokens", autofocus=True, submit_btn='Translate', max_length=512)
-    
+    input_text = gr.Textbox(label="Enter text to translate:", placeholder="Type your text here, maximum 512 tokens",
+                            autofocus=True, submit_btn='Translate', max_length=512) 
     with gr.Row(variant="compact"):
         s_language = gr.Dropdown(choices=langs, value = DEFAULTS[0], label="Source language", interactive=True, scale=2)
         t_language = gr.Dropdown(choices=langs, value = DEFAULTS[1], label="Target language", interactive=True, scale=2)