Feature Extraction
Transformers
Safetensors
qwen2_5_omni_audio_encoder
speech
audio-encoder
flexislm
qwen2.5-omni
Instructions to use FlexiSLM/Qwen2_5-Omni-Audio_Encoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use FlexiSLM/Qwen2_5-Omni-Audio_Encoder with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="FlexiSLM/Qwen2_5-Omni-Audio_Encoder")# Load model directly from transformers import Qwen2_5OmniAudioEncoder model = Qwen2_5OmniAudioEncoder.from_pretrained("FlexiSLM/Qwen2_5-Omni-Audio_Encoder", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "activation_dropout": 0.0, | |
| "activation_function": "gelu", | |
| "architectures": [ | |
| "Qwen2_5OmniAudioEncoder" | |
| ], | |
| "attention_dropout": 0.0, | |
| "d_model": 1280, | |
| "dropout": 0.0, | |
| "encoder_attention_heads": 20, | |
| "encoder_ffn_dim": 5120, | |
| "encoder_layers": 32, | |
| "initializer_range": 0.02, | |
| "max_source_positions": 1500, | |
| "model_type": "qwen2_5_omni_audio_encoder", | |
| "n_window": 100, | |
| "num_hidden_layers": 32, | |
| "num_mel_bins": 128, | |
| "output_dim": 3584, | |
| "scale_embedding": false, | |
| "torch_dtype": "bfloat16" | |
| } | |