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
LiquidCodecFeatureExtractor preprocessor_config.json; n_q -> num_quantizers (huggingface/transformers#50393)
Browse files- config.json +2 -4
- preprocessor_config.json +12 -0
config.json
CHANGED
|
@@ -55,7 +55,6 @@
|
|
| 55 |
"head_dim": 64,
|
| 56 |
"hidden_act": "silu",
|
| 57 |
"hidden_size": 512,
|
| 58 |
-
"hop_length": 320,
|
| 59 |
"initializer_range": 0.02,
|
| 60 |
"intermediate_size": 2304,
|
| 61 |
"layer_types": [
|
|
@@ -86,8 +85,7 @@
|
|
| 86 |
"sliding_window": null,
|
| 87 |
"use_attention_gate": true,
|
| 88 |
"use_cache": false,
|
| 89 |
-
"use_sandwich_norm": true
|
| 90 |
-
"win_length": 1280
|
| 91 |
},
|
| 92 |
"fsq_levels": [
|
| 93 |
8,
|
|
@@ -97,7 +95,7 @@
|
|
| 97 |
],
|
| 98 |
"initializer_range": 0.02,
|
| 99 |
"model_type": "liquid_codec",
|
| 100 |
-
"
|
| 101 |
"quantizer_dim": 256,
|
| 102 |
"sampling_rate": 24000,
|
| 103 |
"transformers_version": "5.23.0.dev0"
|
|
|
|
| 55 |
"head_dim": 64,
|
| 56 |
"hidden_act": "silu",
|
| 57 |
"hidden_size": 512,
|
|
|
|
| 58 |
"initializer_range": 0.02,
|
| 59 |
"intermediate_size": 2304,
|
| 60 |
"layer_types": [
|
|
|
|
| 85 |
"sliding_window": null,
|
| 86 |
"use_attention_gate": true,
|
| 87 |
"use_cache": false,
|
| 88 |
+
"use_sandwich_norm": true
|
|
|
|
| 89 |
},
|
| 90 |
"fsq_levels": [
|
| 91 |
8,
|
|
|
|
| 95 |
],
|
| 96 |
"initializer_range": 0.02,
|
| 97 |
"model_type": "liquid_codec",
|
| 98 |
+
"num_quantizers": 12,
|
| 99 |
"quantizer_dim": 256,
|
| 100 |
"sampling_rate": 24000,
|
| 101 |
"transformers_version": "5.23.0.dev0"
|
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 |
+
}
|