whisper-large-v3-turbo-no-numbers

Whisper-large-v3-turbo-no-numbers

Code for model creation git

Model info

This is a version of openai/whisper-large-v3-turbo model without number tokens (token ids corresponding to numbers are excluded). NO fine-tuning was used.

Phrases with spoken numbers will be transcribed with numbers as words. It can be useful for TTS data preparation.

Example: Instead of "25" this model will transcribe phrase as "twenty five".

Usage

transformers version 4.45.2

Model can be used as an original whisper:

>>> from transformers import WhisperProcessor, WhisperForConditionalGeneration
>>> import torchaudio

>>> # load audio
>>> wav, sr = torchaudio.load("audio.wav")

>>> # load model and processor
>>> processor = WhisperProcessor.from_pretrained("waveletdeboshir/whisper-large-v3-turbo-no-numbers")
>>> model = WhisperForConditionalGeneration.from_pretrained("waveletdeboshir/whisper-large-v3-turbo-no-numbers")

>>> input_features = processor(wav[0], sampling_rate=sr, return_tensors="pt").input_features 

>>> # generate token ids
>>> predicted_ids = model.generate(input_features)
>>> # decode token ids to text
>>> transcription = processor.batch_decode(predicted_ids, skip_special_tokens=False)
['<|startoftranscript|><|en|><|transcribe|><|notimestamps|> Twenty seven years. <|endoftext|>']

The context tokens can be removed from the start of the transcription by setting skip_special_tokens=True.