Feature Extraction
Transformers
Safetensors
liquid_codec
liquid
lfm3
audio
audio-codec
speech
streaming
edge
multilingual
custom_code
Instructions to use eustlb/Liquid-Codec with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use eustlb/Liquid-Codec with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="eustlb/Liquid-Codec", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("eustlb/Liquid-Codec", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Transformers-native config and feature extractor
Browse files- config.json +89 -32
- preprocessor_config.json +12 -0
config.json
CHANGED
|
@@ -1,45 +1,102 @@
|
|
| 1 |
{
|
| 2 |
-
"transformers_version": "5.19.0.dev0",
|
| 3 |
"architectures": [
|
| 4 |
"LiquidCodecModel"
|
| 5 |
],
|
| 6 |
-
"
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
"
|
| 13 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
},
|
| 15 |
-
"
|
| 16 |
-
|
| 17 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
},
|
| 19 |
-
"
|
| 20 |
-
"
|
| 21 |
-
"
|
| 22 |
-
"
|
| 23 |
-
"
|
| 24 |
-
"stft_win_length": 1280,
|
| 25 |
-
"stft_frame_stack": 6,
|
| 26 |
-
"quantizer_dim": 256,
|
| 27 |
-
"fsq_levels": [
|
| 28 |
8,
|
| 29 |
7,
|
| 30 |
6,
|
| 31 |
6
|
| 32 |
],
|
| 33 |
-
"n_q": 12,
|
| 34 |
-
"decoder_window": 30,
|
| 35 |
"sampling_rate": 24000,
|
| 36 |
-
"
|
| 37 |
-
"model_type": "liquid_codec",
|
| 38 |
-
"output_attentions": false,
|
| 39 |
-
"sample_rate": 24000,
|
| 40 |
-
"frame_samples": 1920,
|
| 41 |
-
"auto_map": {
|
| 42 |
-
"AutoConfig": "configuration_liquid_codec.LiquidCodecConfig",
|
| 43 |
-
"AutoModel": "modeling_liquid_codec.LiquidCodecModel"
|
| 44 |
-
}
|
| 45 |
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"LiquidCodecModel"
|
| 4 |
],
|
| 5 |
+
"decoder_config": {
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"conv_L_cache": 7,
|
| 9 |
+
"conv_bias": false,
|
| 10 |
+
"frame_stack": 6,
|
| 11 |
+
"head_dim": 64,
|
| 12 |
+
"hidden_size": 512,
|
| 13 |
+
"hop_length": 320,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 2304,
|
| 16 |
+
"layer_types": [
|
| 17 |
+
"conv",
|
| 18 |
+
"conv",
|
| 19 |
+
"sliding_attention",
|
| 20 |
+
"conv",
|
| 21 |
+
"sliding_attention",
|
| 22 |
+
"conv",
|
| 23 |
+
"sliding_attention",
|
| 24 |
+
"conv"
|
| 25 |
+
],
|
| 26 |
+
"max_position_embeddings": 131072,
|
| 27 |
+
"model_type": "liquid_codec_decoder",
|
| 28 |
+
"n_fft": 1280,
|
| 29 |
+
"norm_eps": 1e-05,
|
| 30 |
+
"num_attention_heads": 8,
|
| 31 |
+
"num_hidden_layers": 8,
|
| 32 |
+
"num_key_value_heads": 2,
|
| 33 |
+
"quantization_dim": 256,
|
| 34 |
+
"rope_parameters": {
|
| 35 |
+
"sliding_attention": {
|
| 36 |
+
"partial_rotary_factor": 1.0,
|
| 37 |
+
"rope_theta": 1000000.0,
|
| 38 |
+
"rope_type": "default"
|
| 39 |
+
}
|
| 40 |
+
},
|
| 41 |
+
"sliding_window": 30,
|
| 42 |
+
"use_attention_gate": true,
|
| 43 |
+
"use_cache": false,
|
| 44 |
+
"use_sandwich_norm": true,
|
| 45 |
+
"win_length": 1280
|
| 46 |
},
|
| 47 |
+
"dtype": "bfloat16",
|
| 48 |
+
"encoder_config": {
|
| 49 |
+
"attention_bias": false,
|
| 50 |
+
"attention_dropout": 0.0,
|
| 51 |
+
"conv_L_cache": 7,
|
| 52 |
+
"conv_bias": false,
|
| 53 |
+
"embedder_hidden_act": "silu",
|
| 54 |
+
"embedder_hidden_size": 256,
|
| 55 |
+
"frame_stack": 6,
|
| 56 |
+
"head_dim": 64,
|
| 57 |
+
"hidden_size": 512,
|
| 58 |
+
"initializer_range": 0.02,
|
| 59 |
+
"intermediate_size": 2304,
|
| 60 |
+
"layer_types": [
|
| 61 |
+
"conv",
|
| 62 |
+
"conv",
|
| 63 |
+
"full_attention",
|
| 64 |
+
"conv",
|
| 65 |
+
"full_attention",
|
| 66 |
+
"conv",
|
| 67 |
+
"full_attention",
|
| 68 |
+
"conv"
|
| 69 |
+
],
|
| 70 |
+
"max_position_embeddings": 131072,
|
| 71 |
+
"model_type": "liquid_codec_encoder",
|
| 72 |
+
"n_fft": 1280,
|
| 73 |
+
"norm_eps": 1e-05,
|
| 74 |
+
"num_attention_heads": 8,
|
| 75 |
+
"num_hidden_layers": 8,
|
| 76 |
+
"num_key_value_heads": 2,
|
| 77 |
+
"quantization_dim": 256,
|
| 78 |
+
"rope_parameters": {
|
| 79 |
+
"full_attention": {
|
| 80 |
+
"partial_rotary_factor": 1.0,
|
| 81 |
+
"rope_theta": 1000000.0,
|
| 82 |
+
"rope_type": "default"
|
| 83 |
+
}
|
| 84 |
+
},
|
| 85 |
+
"sliding_window": null,
|
| 86 |
+
"use_attention_gate": true,
|
| 87 |
+
"use_cache": false,
|
| 88 |
+
"use_sandwich_norm": true
|
| 89 |
},
|
| 90 |
+
"initializer_range": 0.02,
|
| 91 |
+
"model_type": "liquid_codec",
|
| 92 |
+
"num_quantizers": 12,
|
| 93 |
+
"quantization_dim": 256,
|
| 94 |
+
"quantization_levels": [
|
|
|
|
|
|
|
|
|
|
|
|
|
| 95 |
8,
|
| 96 |
7,
|
| 97 |
6,
|
| 98 |
6
|
| 99 |
],
|
|
|
|
|
|
|
| 100 |
"sampling_rate": 24000,
|
| 101 |
+
"transformers_version": "5.24.0.dev0"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 102 |
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"feature_extractor_type": "LiquidCodecFeatureExtractor",
|
| 3 |
+
"feature_size": 1923,
|
| 4 |
+
"frame_stack": 6,
|
| 5 |
+
"hop_length": 320,
|
| 6 |
+
"n_fft": 1280,
|
| 7 |
+
"padding_side": "right",
|
| 8 |
+
"padding_value": 0.0,
|
| 9 |
+
"return_attention_mask": true,
|
| 10 |
+
"sampling_rate": 24000,
|
| 11 |
+
"win_length": 1280
|
| 12 |
+
}
|