feat(engine): 字幕引擎添加在终端直接显示字幕的功能

docs/api-docs/caption-engine.md

@@ -64,6 +64,7 @@ Python 端监听到的音频流转换为的字幕数据。
 {
   command: "translation",
   time_s: string,
+  text: string,
   translation: string
 }
 ```

engine/main.py

@@ -2,7 +2,7 @@ import wave
 import argparse
 import threading
 import datetime
-from utils import stdout, stdout_cmd
+from utils import stdout, stdout_cmd, change_caption_display
 from utils import shared_data, start_server
 from utils import merge_chunk_channels, resample_chunk_mono
 from audio2text import GummyRecognizer
@@ -142,11 +142,12 @@ def main_sosv(a: int, c: int, sosv: str, s: str, t: str, tm: str, omn: str, r: b
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(description='Convert system audio stream to text')
     # all
-    parser.add_argument('-e', '--caption_engine', default='gummy', help='Caption engine: gummy or vosk')
+    parser.add_argument('-e', '--caption_engine', default='gummy', help='Caption engine: gummy or vosk or sosv')
     parser.add_argument('-a', '--audio_type', default=0, help='Audio stream source: 0 for output, 1 for input')
     parser.add_argument('-c', '--chunk_rate', default=10, help='Number of audio stream chunks collected per second')
     parser.add_argument('-p', '--port', default=0, help='The port to run the server on, 0 for no server')
-    parser.add_argument('-t', '--target_language', default='zh', help='Target language code, "none" for no translation')
+    parser.add_argument('-d', '--display_caption', default=0, help='Display caption on terminal, 0 for no display, 1 for display')
+    parser.add_argument('-t', '--target_language', default='none', help='Target language code, "none" for no translation')
     parser.add_argument('-r', '--record', default=0, help='Whether to record the audio, 0 for no recording, 1 for recording')
     parser.add_argument('-rp', '--record_path', default='', help='Path to save the recorded audio')
     # gummy and sosv
@@ -167,6 +168,10 @@ if __name__ == "__main__":
     else:
         start_server(int(args.port))
     
+    if int(args.display_caption) != 0:
+        change_caption_display(True)
+        print("Caption will be displayed on terminal")
+
     if args.caption_engine == 'gummy':
         main_gummy(
             args.source_language,

engine/utils/__init__.py

@@ -1,5 +1,6 @@
 from .audioprcs import merge_chunk_channels, resample_chunk_mono
 from .sysout import stdout, stdout_err, stdout_cmd, stdout_obj, stderr
+from .sysout import change_caption_display
 from .shared import shared_data
 from .server import start_server
 from .translation import ollama_translate, google_translate

engine/utils/sysout.py

@@ -1,5 +1,10 @@
 import sys
 import json
+import sherpa_onnx
+
+display_caption = False
+caption_index = -1
+display = sherpa_onnx.Display()
 
 def stdout(text: str):
     stdout_cmd("print", text)
@@ -12,7 +17,39 @@ def stdout_cmd(command: str, content = ""):
     sys.stdout.write(json.dumps(msg) + "\n")
     sys.stdout.flush()
 
+def change_caption_display(val: bool):
+    global display_caption
+    display_caption = val
+
+def caption_display(obj):
+    global display_caption
+    global caption_index
+    global display
+
+    if caption_index >=0 and caption_index != int(obj['index']):
+        display.finalize_current_sentence()
+    caption_index = int(obj['index'])
+    full_text = f"{obj['text']} {obj['translation']}"
+    display.update_text(full_text)
+    display.display()
+
+def translation_display(obj):
+    global original_caption
+    global display
+    full_text = f"{obj['text']} {obj['translation']}"
+    display.update_text(full_text)
+    display.display()
+    display.finalize_current_sentence()
+
 def stdout_obj(obj):
+    global display_caption
+    print(obj['command'], display_caption)
+    if obj['command'] == 'caption' and display_caption:
+        caption_display(obj)
+        return
+    if obj['command'] == 'translation' and display_caption:
+        translation_display(obj)
+        return
     sys.stdout.write(json.dumps(obj) + "\n")
     sys.stdout.flush()
 

engine/utils/translation.py

@@ -33,6 +33,7 @@ def ollama_translate(model: str, target: str, text: str, time_s: str):
     stdout_obj({
         "command": "translation",
         "time_s": time_s,
+        "text": text,
         "translation": content.strip()
     })
 
@@ -43,6 +44,7 @@ def google_translate(model: str, target: str, text: str, time_s: str):
         stdout_obj({
             "command": "translation",
             "time_s": time_s,
+            "text": text,
             "translation": res.text
         })
     except Exception as e: