hackingthemarkets/chatgpt-api-whisper-api-voice-assistant

chatgpt api and whisper api tutorial - voice conversation with therapist

chatgpt-api-whisper-api-voice-assistant's Issues

Hi Larry!~

Can I have your email ? I want to communicate about a project, thanks

Error on submit

I got an error when click submit audio file:

File "c:\Users\iroza\Desktop\Projects\Project3\therapist.py", line 10, in transcribe
audio_file = open(audio, "rb")
TypeError: expected str, bytes or os.PathLike object, not NoneType

I installed ffmpeg and ffrobe.

Can somebody help me?

.

.

Problem with wrong audio type

Hey all,

i can´t fix this Problem. ffmpeg installed finde, the audi file is saved as .wav but still this error stops my transcription.
Any Ideas for this fix. Iam on windows system, maybe there are codec error?

Error: openai.error.InvalidRequestError: Invalid file format. Supported formats: ['m4a', 'mp3', 'webm', 'mp4', 'mpga', 'wav', 'mpeg']

Small issue on ffprobe audio

Good work @PartTimeAI

RuntimeError: Cannot load audio from file: ffprobe not found. Please install ffmpeg in your system to use non-WAV audio file formats and make sure ffprobe is in your PATH.

I installed ffrobe also. still getting this error. can you look at this fix?

full message below..

Traceback (most recent call last):
File "C:\Users\44754\anaconda3\lib\site-packages\gradio\processing_utils.py", line 200, in audio_from_file
audio = AudioSegment.from_file(filename)
File "C:\Users\44754\anaconda3\lib\site-packages\pydub\audio_segment.py", line 728, in from_file
info = mediainfo_json(orig_file, read_ahead_limit=read_ahead_limit)
File "C:\Users\44754\anaconda3\lib\site-packages\pydub\utils.py", line 274, in mediainfo_json
res = Popen(command, stdin=stdin_parameter, stdout=PIPE, stderr=PIPE)
File "C:\Users\44754\anaconda3\lib\subprocess.py", line 858, in init
self._execute_child(args, executable, preexec_fn, close_fds,
File "C:\Users\44754\anaconda3\lib\subprocess.py", line 1311, in _execute_child
hp, ht, pid, tid = _winapi.CreateProcess(executable, args,
FileNotFoundError: [WinError 2] The system cannot find the file specified

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "C:\Users\44754\anaconda3\lib\site-packages\gradio\routes.py", line 384, in run_predict
output = await app.get_blocks().process_api(
File "C:\Users\44754\anaconda3\lib\site-packages\gradio\blocks.py", line 1030, in process_api
inputs = self.preprocess_data(fn_index, inputs, state)
File "C:\Users\44754\anaconda3\lib\site-packages\gradio\blocks.py", line 922, in preprocess_data
processed_input.append(block.preprocess(inputs[i]))
File "C:\Users\44754\anaconda3\lib\site-packages\gradio\components.py", line 2087, in preprocess
sample_rate, data = processing_utils.audio_from_file(
File "C:\Users\44754\anaconda3\lib\site-packages\gradio\processing_utils.py", line 210, in audio_from_file
raise RuntimeError(msg) from e
RuntimeError: Cannot load audio from file: ffprobe not found. Please install ffmpeg in your system to use non-WAV audio file formats and make sure ffprobe is in your PATH.