Merge pull request #73 from jhormigo/hls_support

Support for HLS transcription

README.md

@@ -41,6 +41,12 @@ Unlike traditional speech recognition systems that rely on continuous audio stre
     ```
     This command captures audio from the microphone and sends it to the server for transcription. It uses the same options as the previous command, enabling the multilingual feature and specifying the target language and task.
 
+    - To trasncribe from a HLS stream:
+    ```python
+      client = TranscriptionClient(host, port, is_multilingual=True, lang="en", translate=False) 
+      client(hls_url="http://as-hls-ww-live.akamaized.net/pool_904/live/ww/bbc_1xtra/bbc_1xtra.isml/bbc_1xtra-audio%3d96000.norewind.m3u8") 
+    ```
+    This command streams audio into the server from a HLS stream. It uses the same options as the previous command, enabling the multilingual feature and specifying the target language and task.
 
 ## Transcribe audio from browser
 - Run the server

whisper_live/client.py

@@ -344,6 +344,42 @@ class Client:
             wavfile.setframerate(self.rate)
             wavfile.writeframes(frames)
 
+    def process_hls_stream(self, hls_url):
+        """
+        Connect to an HLS source, process the audio stream, and send it for transcription.
+
+        Args:
+            hls_url (str): The URL of the HLS stream source.
+        """
+        print("[INFO]: Connecting to HLS stream...")
+        process = None  # Initialize process to None
+
+        try:
+            # Connecting to the HLS stream using ffmpeg-python
+            process = (
+                ffmpeg
+                .input(hls_url, threads=0)
+                .output('-', format='s16le', acodec='pcm_s16le', ac=1, ar=self.rate)
+                .run_async(pipe_stdout=True, pipe_stderr=True)
+            )
+
+            # Process the stream
+            while True:
+                in_bytes = process.stdout.read(self.chunk * 2)  # 2 bytes per sample
+                if not in_bytes:
+                    break
+                audio_array = self.bytes_to_float_array(in_bytes)
+                self.send_packet_to_server(audio_array.tobytes())
+
+        except Exception as e:
+            print(f"[ERROR]: Failed to connect to HLS stream: {e}")
+        finally:
+            if process:
+                process.kill()
+
+        print("[INFO]: HLS stream processing finished.")
+
+
     def record(self, out_file="output_recording.wav"):
         """
         Record audio data from the input stream and save it to a WAV file.
@@ -464,7 +500,7 @@ class TranscriptionClient:
     def __init__(self, host, port, is_multilingual=False, lang=None, translate=False):
         self.client = Client(host, port, is_multilingual, lang, translate)
 
-    def __call__(self, audio=None):
+    def __call__(self, audio=None, hls_url=None):
         """
         Start the transcription process.
 
@@ -483,8 +519,10 @@ class TranscriptionClient:
                 return
             pass
         print("[INFO]: Server Ready!")
-        if audio is not None:
+        if hls_url is not None:
+            self.client.process_hls_stream(hls_url)
+        elif audio is not None:
             resampled_file = resample(audio)
             self.client.play_file(resampled_file)
         else:
-            self.client.record()
+            self.client.record()