Merge branch 'main' into ayo-logging-fixes

README.md

@@ -183,7 +183,7 @@ online.init()  # refresh if you're going to re-use the object for the next audio
 
 ### Server -- real-time from mic
 
-`whisper_online_server.py` has the same model options as `whisper_online.py`, plus `--host` and `--port` of the TCP connection. See help message (`-h` option).
+`whisper_online_server.py` has the same model options as `whisper_online.py`, plus `--host` and `--port` of the TCP connection and the `--warmup-file`. See the help message (`-h` option).
 
 Client example:
 

line_packet.py

@@ -2,8 +2,6 @@
 
 """Functions for sending and receiving individual lines of text over a socket.
 
-Used by marian-server-server.py to communicate with the Marian worker.
-
 A line is transmitted using one or more fixed-size packets of UTF-8 bytes
 containing:
 
@@ -11,6 +9,7 @@ containing:
 
   - Zero or more \0 bytes as required to pad the packet to PACKET_SIZE
 
+Originally from the UEDIN team of the ELITR project. 
 """
 
 PACKET_SIZE = 65536

whisper_online.py

@@ -559,7 +559,7 @@ def add_shared_args(parser):
 
 def asr_factory(args, logfile=sys.stderr):
     """
-    Creates and configures an ASR instance based on the specified backend and arguments.
+    Creates and configures an ASR and ASR Online instance based on the specified backend and arguments.
     """
     backend = args.backend
     if backend == "openai-api":
@@ -584,8 +584,23 @@ def asr_factory(args, logfile=sys.stderr):
         logging.info("Setting VAD filter")
         asr.use_vad()
 
-    return asr
+    language = args.lan
+    if args.task == "translate":
+        asr.set_translate_task()
+        tgt_language = "en"  # Whisper translates into English
+    else:
+        tgt_language = language  # Whisper transcribes in this language
+
+    # Create the tokenizer
+    if args.buffer_trimming == "sentence":
+        tokenizer = create_tokenizer(tgt_language)
+    else:
+        tokenizer = None
 
+    # Create the OnlineASRProcessor
+    online = OnlineASRProcessor(asr,tokenizer,logfile=logfile,buffer_trimming=(args.buffer_trimming, args.buffer_trimming_sec))
+
+    return asr, online
 ## main:
 
 if __name__ == "__main__":
@@ -613,27 +628,13 @@ if __name__ == "__main__":
     duration = len(load_audio(audio_path))/SAMPLING_RATE
     logging.info("Audio duration is: %2.2f seconds" % duration)
 
-    asr = asr_factory(args, logfile=logfile)
-    language = args.lan
-
-    if args.task == "translate":
-        asr.set_translate_task()
-        tgt_language = "en"  # Whisper translates into English
-    else:
-        tgt_language = language  # Whisper transcribes in this language
-
+    asr, online = asr_factory(args, logfile=logfile)
     min_chunk = args.min_chunk_size
-    if args.buffer_trimming == "sentence":
-        tokenizer = create_tokenizer(tgt_language)
-    else:
-        tokenizer = None
-    online = OnlineASRProcessor(asr,tokenizer,logfile=logfile,buffer_trimming=(args.buffer_trimming, args.buffer_trimming_sec))
-
 
     # load the audio into the LRU cache before we start the timer
     a = load_audio_chunk(audio_path,0,1)
 
-    # warm up the ASR, because the very first transcribe takes much more time than the other
+    # warm up the ASR because the very first transcribe takes much more time than the other
     asr.transcribe(a)
 
     beg = args.start_at

whisper_online_server.py

@@ -12,6 +12,8 @@ parser = argparse.ArgumentParser()
 # server options
 parser.add_argument("--host", type=str, default='localhost')
 parser.add_argument("--port", type=int, default=43007)
+parser.add_argument("--warmup-file", type=str, dest="warmup_file", 
+        help="The path to a speech audio wav file to warm up Whisper so that the very first chunk processing is fast. It can be e.g. https://github.com/ggerganov/whisper.cpp/raw/master/samples/jfk.wav .")
 
 parser.add_argument("-l", "--log-level", dest="log_level", 
                     choices=['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL'],
@@ -33,37 +35,28 @@ SAMPLING_RATE = 16000
 
 size = args.model
 language = args.lan
-
-asr = asr_factory(args)
-
-if args.task == "translate":
-    asr.set_translate_task()
-    tgt_language = "en"
-else:
-    tgt_language = language
-
+asr, online = asr_factory(args)
 min_chunk = args.min_chunk_size
 
+
 if args.buffer_trimming == "sentence":
     tokenizer = create_tokenizer(tgt_language)
 else:
     tokenizer = None
 online = OnlineASRProcessor(asr,tokenizer,buffer_trimming=(args.buffer_trimming, args.buffer_trimming_sec))
 
-
-
-demo_audio_path = "cs-maji-2.16k.wav"
-if os.path.exists(demo_audio_path):
-    # load the audio into the LRU cache before we start the timer
-    logging.debug(f"Warming up on {demo_audio_path}")
-    a = load_audio_chunk(demo_audio_path,0,1)
-
-    # TODO: it should be tested whether it's meaningful
-    # warm up the ASR, because the very first transcribe takes much more time than the other
-    asr.transcribe(a)
-    logging.debug("Whisper is warmed up")
+# warm up the ASR because the very first transcribe takes more time than the others. 
+# Test results in https://github.com/ufal/whisper_streaming/pull/81
+msg = "Whisper is not warmed up. The first chunk processing may take longer."
+if args.warmup_file:
+    if os.path.isfile(args.warmup_file):
+        a = load_audio_chunk(args.warmup_file,0,1)
+        asr.transcribe(a)
+        print("INFO: Whisper is warmed up.",file=sys.stderr)
+    else:
+        print("WARNING: The warm up file is not available. "+msg,file=sys.stderr)
 else:
-    logging.debug("Whisper is not warmed up")
+    print("WARNING: " + msg, file=sys.stderr)
 
 
 ######### Server objects