From b4d9997fc6ca77f6d69466b239bca0cf02278b28 Mon Sep 17 00:00:00 2001 From: ceb515 Date: Mon, 12 Feb 2024 12:01:13 -0500 Subject: [PATCH] Various changes Add requirements.txt Update secrets file with new options Added option to transcode voice to text --- .gitignore | 1 + pagebot.py | 34 ++++++++++++++++++++++++++++++---- requirements.txt | 3 +++ sample-secrets_file.py | 2 ++ 4 files changed, 36 insertions(+), 4 deletions(-) create mode 100644 requirements.txt diff --git a/.gitignore b/.gitignore index 97e75e2..7ea4e73 100644 --- a/.gitignore +++ b/.gitignore @@ -1,5 +1,6 @@ # Ignore ffmpeg executable ffmpeg +ffprobe # Ignore secrets file secrets_file.py \ No newline at end of file diff --git a/pagebot.py b/pagebot.py index f543479..d9fff1b 100644 --- a/pagebot.py +++ b/pagebot.py @@ -6,6 +6,7 @@ import time import secrets_file from watchdog.observers import Observer from watchdog.events import FileSystemEventHandler +import speech_recognition as sr ## file handler @@ -15,25 +16,46 @@ class MyHandler(FileSystemEventHandler): return filepath = event.src_path filename, file_extension = os.path.splitext(filepath) + if file_extension.lower() == '.amr': + time.sleep(10) + os.remove(filepath) + print("Removing AMR.") if file_extension.lower() == '.mp3': print("New MP3!") + text = "" + if secrets_file.speech_to_text: + text = convert_to_text(filepath) mp4_file = convert_to_mp4(filepath) - client.loop.create_task(upload_to_discord(mp4_file)) + client.loop.create_task(upload_to_discord(mp4_file,text)) + os.remove(filepath) ##convert mp3 to mp4 def convert_to_mp4(mp3_file): try: + time.sleep(10) mp4_file = os.path.splitext(mp3_file)[0] + '.mp4' command = f'./ffmpeg -loop 1 -i img/blacksmall.jpg -i "{mp3_file}" -c:a aac -b:a 192k -c:v libx264 -pix_fmt yuv420p -shortest "{mp4_file}"' subprocess.run(command, shell=True) - os.remove(mp3_file) return mp4_file except Exception as e: print(f"Error during conversion: {e}") return None + +def convert_to_text(mp3_file): + command = f'./ffmpeg -i "{mp3_file}" output_audio.wav' + subprocess.run(command, shell=True) + r = sr.Recognizer() + # Load the audio file + with sr.AudioFile("output_audio.wav") as source: + data = r.record(source) + # Convert speech to text + text = r.recognize_google(data) + os.remove("output_audio.wav") + return (text) + ## upload to discord -async def upload_to_discord(mp4_file): +async def upload_to_discord(mp4_file,text): ## Check to make sure conversion worked. if mp4_file is None: print("Conversion failed. Skipping upload.") @@ -45,7 +67,11 @@ async def upload_to_discord(mp4_file): ## Send Video with name with open(mp4_file, 'rb') as f: await channel.send(filename,file=discord.File(f)) - + if secrets_file.delete_after_upload: + os.remove(mp4_file) + ## Send transcribed voice if present. + if (text != ""): + await channel.send(f"The following text was transcoded from the recording: \n{text}") ## Ping users with the appropriate number role_name = filename.split('-', 1)[0].strip() role = discord.utils.get(channel.guild.roles, name=role_name) diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..242c86a --- /dev/null +++ b/requirements.txt @@ -0,0 +1,3 @@ +discord.py==2.3.2 +SpeechRecognition==3.10.1 +watchdog==4.0.0s \ No newline at end of file diff --git a/sample-secrets_file.py b/sample-secrets_file.py index 4cb27eb..379d3e3 100644 --- a/sample-secrets_file.py +++ b/sample-secrets_file.py @@ -1,3 +1,5 @@ key = 'Bot Token' watch_folder = '/path/to/folder' channel_id = channel_id_number +delete_after_upload=True +speech_to_text = True \ No newline at end of file