-
Notifications
You must be signed in to change notification settings - Fork 340
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Support for openai Whisper #466
Comments
How should I apply it to ASR? Thank you! |
Hey! Pretty sure it is available in |
I added adapters to whisper in (HenningBuhl@544ae05) I am currently testing it and want to make a PR soon. |
Hello @HenningBuhl `import torch model_name = "openai/whisper-small" #Convert dataset to DataFrame df = pd.DataFrame(data) #Convert dataset to DataFrame df = pd.DataFrame(data) common_voice["train"] = Dataset.from_pandas(common_voice_train) #Extract, Tokenize and Process print('###############Extract, Tokenize and Process Is Complete################') #Prepare Data def prepare_dataset(batch):
common_voice = common_voice.map(prepare_dataset, remove_columns=common_voice.column_names["train"], num_proc=1) print('###############Data Preparation Is Complete################') @DataClass
data_collator = DataCollatorSpeechSeq2SeqWithPadding(processor=processor) print('###############Data Collator Is Complete################') metric = evaluate.load("wer") def flattenList(id_list): def compute_metrics(pred):
print('###############Compute metrics Is Complete################') #Define the adapter layers #Set up your training arguments and data #Create a Trainer and train the model on your task-specific dataset print('###############Training Arguments placing Is Complete################') trainer.train() trainer.evaluate() |
🌟 New adapter setup
Support for openai Whisper
Add adapter integration for whisper.
Open source status
The text was updated successfully, but these errors were encountered: