Instructions to use huseinzol05/conformer-super-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use huseinzol05/conformer-super-tiny with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="huseinzol05/conformer-super-tiny", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("huseinzol05/conformer-super-tiny", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "ConformerEncoder" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "conformer.ConformerConfig", | |
| "AutoModel": "conformer.ConformerEncoder" | |
| }, | |
| "conformer_depthwise_conv_kernel_size": 31, | |
| "conformer_dropout": 0.0, | |
| "conformer_ffn_dim": 576, | |
| "conformer_input_dim": 144, | |
| "conformer_num_heads": 4, | |
| "conformer_num_layers": 4, | |
| "ctc_loss_reduction": "mean", | |
| "ctc_zero_infinity": true, | |
| "input_dim": 80, | |
| "model_type": "conformer", | |
| "output_dim": 40, | |
| "pad_token_id": 39, | |
| "time_reduction_stride": 4, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.35.2" | |
| } | |