Feature Extraction
Transformers
Safetensors
English
custom_model
multi-modal
speech-language
custom_code
Eval Results (legacy)
Instructions to use skit-ai/speechllm-1.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use skit-ai/speechllm-1.5B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="skit-ai/speechllm-1.5B", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("skit-ai/speechllm-1.5B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "SpeechLLMModel" | |
| ], | |
| "audio_enc_dim": 1024, | |
| "audio_encoder_name": "microsoft/wavlm-large", | |
| "audio_processor_name": "microsoft/wavlm-base", | |
| "auto_map": { | |
| "AutoConfig": "config.SpeechLLMModelConfig", | |
| "AutoModel": "model.SpeechLLMModel" | |
| }, | |
| "llm_dim": 2048, | |
| "llm_model_checkpoint": "hf_repo/llm_model_checkpoint", | |
| "llm_model_name": "TinyLlama/TinyLlama-1.1B-Chat-v1.0", | |
| "model_type": "custom_model", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.41.2" | |
| } | |