MINI AI
Collection
The mini AI series ; I found that i needed smaller models for other models such as VisionEncoderDecoder : and other models which contain llms as a par • 5 items • Updated
Automatic Speech Recognition
Transformers
Safetensors
English
mistral
text-generation
text-generation-inference
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("LeroyDyer/SpydazWebAI_SpeechEncoderDecoder_Mini548m")
model = AutoModelForCausalLM.from_pretrained("LeroyDyer/SpydazWebAI_SpeechEncoderDecoder_Mini548m")Quick Links
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
- Downloads last month
- 16
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="LeroyDyer/SpydazWebAI_SpeechEncoderDecoder_Mini548m")