Update app.py

app.py

@@ -1,27 +1,17 @@
 from huggingface_hub import InferenceClient
 import gradio as gr
+import re
 
-client = InferenceClient(
-    "mistralai/Mixtral-8x7B-Instruct-v0.1"
-)
+client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
 
+def parse_srt(content):
+    """Parse the SRT file content, yielding text lines and skipping timestamps, line numbers, or blank lines."""
+    lines = content.split("\n")
+    for line in lines:
+        if not line.isdigit() and not re.match(r'\d{2}:\d{2}:\d{2},\d{3} --> \d{2}:\d{2}:\d{2},\d{3}', line) and line.strip():
+            yield line
 
-def format_prompt(message, history):
-  prompt = "<s>"
-  for user_prompt, bot_response in history:
-    prompt += f"[INST] {user_prompt} [/INST]"
-    prompt += f" {bot_response}</s> "
-  prompt += f"[INST] {message} [/INST]"
-  return prompt
-
-def generate(
-    prompt, history, system_prompt, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,
-):
-    temperature = float(temperature)
-    if temperature < 1e-2:
-        temperature = 1e-2
-    top_p = float(top_p)
-
+def translate_line(line, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0):
     generate_kwargs = dict(
         temperature=temperature,
         max_new_tokens=max_new_tokens,
@@ -31,64 +21,21 @@ def generate(
         seed=42,
     )
 
-    formatted_prompt = format_prompt(f"{system_prompt}, {prompt}", history)
-    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
+    stream = client.text_generation(f"Translate to English: {line}", **generate_kwargs, stream=True, details=True, return_full_text=False)
     output = ""
-
     for response in stream:
         output += response.token.text
-        yield output
     return output
 
-
-additional_inputs=[
-    gr.Textbox(
-        label="System Prompt",
-        max_lines=1,
-        interactive=True,
-    ),
-    gr.Slider(
-        label="Temperature",
-        value=0.9,
-        minimum=0.0,
-        maximum=1.0,
-        step=0.05,
-        interactive=True,
-        info="Higher values produce more diverse outputs",
-    ),
-    gr.Slider(
-        label="Max new tokens",
-        value=256,
-        minimum=0,
-        maximum=1048,
-        step=64,
-        interactive=True,
-        info="The maximum numbers of new tokens",
-    ),
-    gr.Slider(
-        label="Top-p (nucleus sampling)",
-        value=0.90,
-        minimum=0.0,
-        maximum=1,
-        step=0.05,
-        interactive=True,
-        info="Higher values sample more low-probability tokens",
-    ),
-    gr.Slider(
-        label="Repetition penalty",
-        value=1.2,
-        minimum=1.0,
-        maximum=2.0,
-        step=0.05,
-        interactive=True,
-        info="Penalize repeated tokens",
-    )
-]
-
-gr.ChatInterface(
-    fn=generate,
-    chatbot=gr.Chatbot(show_label=False, show_share_button=False, show_copy_button=True, likeable=True, layout="panel"),
-    additional_inputs=additional_inputs,
-    title="Mixtral 46.7B",
-    concurrency_limit=20,
-).launch()
+def translate_srt(file_info):
+    content = file_info['content'].decode("utf-8")
+    translated_lines = [translate_line(line) for line in parse_srt(content)]
+    return "\n".join(translated_lines)
+
+gr.Interface(
+    fn=translate_srt,
+    inputs=gr.File(label="Upload SRT File"),
+    outputs=gr.Textbox(label="Translated Text"),
+    title="SRT Translator",
+    description="Upload an SRT file to translate its content line by line."
+).launch()