Last active
July 2, 2021 08:57
-
-
Save SamuelAlgheriniAI/47eafe84b1029e09c78aa45f85eef561 to your computer and use it in GitHub Desktop.
Here there are the model, variables, folders and path creation and the extension conversion list
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Import the Wav2Vec model and processor | |
model = "facebook/wav2vec2-base-960h" | |
print("Loading model: ", model) | |
processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-base-960h") | |
model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h") | |
#VARIABLES | |
path_base = "Audio files/" #Original speech/audio files folder | |
sr = 16000 #Sampling rate | |
block_length = 30 #Speech chunk size | |
language = "en" | |
expertai_account = "your_expert.ai_email" #Your expert.ai email account | |
expertai_psw = "your_expert.ai_psw" #Your expert.ai psw | |
os.environ["EAI_USERNAME"] = expertai_account | |
os.environ["EAI_PASSWORD"] = expertai_psw | |
#Folders and Path Creation | |
audio_report = "Reports" #This is the folder where your report will be stored | |
path_converted_audio = "converted_files/" #This is the temporary folder for converted audio files | |
resampled_folder = "resampled_files/" #This is the folder for the resampled audio files | |
Path(audio_report).mkdir(parents = True, exist_ok = True) #This creates the reports folder | |
Path(path_converted_audio).mkdir(parents = True, exist_ok = True) #This creates the folder for converted audio files | |
Path(resampled_folder).mkdir(parents = True, exist_ok = True) #This creates the folder for resampled audio files | |
#Conversion List | |
extension_to_convert = ['.mp3','.mp4','.m4a','.flac','.opus'] #List of the supported files types/extensions |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment