metadata
license: mit
language:
- en
library_name: transformers
pipeline_tag: automatic-speech-recognition
Mistral SPEECH-ENCODER-DECODER-MODEL
works fine just add custom training
print('Add Audio...')
#Add Head
# Combine pre-trained encoder and pre-trained decoder to form a Seq2Seq model
_AudioFeatureExtractor = AutoFeatureExtractor.from_pretrained("openai/whisper-small")
_AudioTokenizer = AutoTokenizer.from_pretrained("openai/whisper-small")
_SpeechEncoderDecoder = SpeechEncoderDecoderModel.from_encoder_decoder_pretrained("openai/whisper-small","openai/whisper-small")
# Add Pad tokems
_SpeechEncoderDecoder.config.decoder_start_token_id = _AudioTokenizer.cls_token_id
_SpeechEncoderDecoder.config.pad_token_id = _AudioTokenizer.pad_token_id
LM_MODEL.SpeechEncoderDecoder = _SpeechEncoderDecoder
# Add Sub Components
LM_MODEL.Decoder_AudioTokenizer = _AudioTokenizer
LM_MODEL.Encoder_AudioFeatureExtractor = _AudioFeatureExtractor
LM_MODEL