dasheng-base

>>> model_name = "mispeech/dasheng-base"

>>> from transformers import AutoModel, AutoFeatureExtractor

>>> feature_extractor = AutoFeatureExtractor.from_pretrained(model_name, trust_remote_code=True)
>>> model = AutoModel.from_pretrained(model_name, outputdim=None, trust_remote_code=True)

>>> import torch
>>> inputs = feature_extractor(torch.randn(1, 16000), sampling_rate=sampling_rate, return_tensors="pt")
>>> inputs.input_values.shape
torch.Size([1, 64, 101])   # 64 mel-filterbanks, 101 frames

>>> with torch.no_grad():
...     outputs = model(**inputs)

>>> outputs.hidden_states.shape
torch.Size([1, 25, 768])   # 25 T-F patches (patch size 64x4, no overlap), before mean-pooling

>>> outputs.logits.shape
torch.Size([1, 768])   # mean-pooled embedding (would be logits from a linear layer if `outputdim` was set)