Ai_model_audio

README.md

@@ -1,3 +1,5 @@
+
+
 ---
 license: apache-2.0
 tags:
@@ -54,7 +56,7 @@ NeuCodec is largely based on extending the work of [X-Codec2.0](https://huggingf
 - **Model type:** Neural Audio Codec
 - **License:** apache-2.0
 - **Repository:** https://github.com/neuphonic/neucodec
-- **Paper:** [arXiv](https://arxiv.org/abs/2509.09550)
+- **Paper:** *Coming soon!*
 - **Pre-encoded Datasets:**
   - [Emilia-YODAS-EN](https://huggingface.co/datasets/neuphonic/emilia-yodas-english-neucodec)
   - *More coming soon!*

config.json

@@ -1,129 +0,0 @@
-{
-  "activation_dropout": 0.1,
-  "architectures": [
-    "NeuCodecModel"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "downsampling_ratios": [
-    2,
-    2,
-    4,
-    4,
-    5
-  ],
-  "dtype": "float32",
-  "encoder_hidden_size": 48,
-  "head_dim": 64,
-  "hidden_act": "silu",
-  "hidden_size": 1024,
-  "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "max_position_embeddings": 4096,
-  "model_type": "neucodec",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 12,
-  "num_key_value_heads": 16,
-  "output_sampling_rate": 24000,
-  "pad_token_id": null,
-  "quantization_dim": 2048,
-  "quantization_levels": [
-    4,
-    4,
-    4,
-    4,
-    4,
-    4,
-    4,
-    4
-  ],
-  "rms_norm_eps": 1e-06,
-  "rope_parameters": {
-    "rope_theta": 10000.0,
-    "rope_type": "default"
-  },
-  "sampling_rate": 16000,
-  "semantic_model_config": {
-    "_name_or_path": "facebook/w2v-bert-2.0",
-    "activation_dropout": 0.0,
-    "adapter_act": "relu",
-    "adapter_kernel_size": 3,
-    "adapter_stride": 2,
-    "add_adapter": false,
-    "apply_spec_augment": false,
-    "architectures": [
-      "Wav2Vec2BertModel"
-    ],
-    "attention_dropout": 0.0,
-    "bos_token_id": 1,
-    "classifier_proj_size": 768,
-    "codevector_dim": 768,
-    "conformer_conv_dropout": 0.1,
-    "contrastive_logits_temperature": 0.1,
-    "conv_depthwise_kernel_size": 31,
-    "ctc_loss_reduction": "sum",
-    "ctc_zero_infinity": false,
-    "diversity_loss_weight": 0.1,
-    "dtype": "float32",
-    "eos_token_id": 2,
-    "feat_proj_dropout": 0.0,
-    "feat_quantizer_dropout": 0.0,
-    "feature_projection_input_dim": 160,
-    "final_dropout": 0.1,
-    "hidden_act": "swish",
-    "hidden_dropout": 0.0,
-    "hidden_size": 1024,
-    "initializer_range": 0.02,
-    "intermediate_size": 4096,
-    "layer_norm_eps": 1e-05,
-    "layerdrop": 0.1,
-    "left_max_position_embeddings": 64,
-    "mask_feature_length": 10,
-    "mask_feature_min_masks": 0,
-    "mask_feature_prob": 0.0,
-    "mask_time_length": 10,
-    "mask_time_min_masks": 2,
-    "mask_time_prob": 0.05,
-    "max_source_positions": 5000,
-    "model_type": "wav2vec2-bert",
-    "num_adapter_layers": 1,
-    "num_attention_heads": 16,
-    "num_codevector_groups": 2,
-    "num_codevectors_per_group": 320,
-    "num_hidden_layers": 16,
-    "num_negatives": 100,
-    "output_hidden_size": 1024,
-    "pad_token_id": 0,
-    "position_embeddings_type": "relative_key",
-    "proj_codevector_dim": 768,
-    "right_max_position_embeddings": 8,
-    "rotary_embedding_base": 10000,
-    "tdnn_dilation": [
-      1,
-      2,
-      3,
-      1,
-      1
-    ],
-    "tdnn_dim": [
-      512,
-      512,
-      512,
-      512,
-      1500
-    ],
-    "tdnn_kernel": [
-      5,
-      3,
-      3,
-      1,
-      1
-    ],
-    "use_intermediate_ffn_before_adapter": false,
-    "use_weighted_layer_sum": false,
-    "vocab_size": null,
-    "xvector_output_dim": 512
-  },
-  "tie_word_embeddings": false,
-  "transformers_version": "5.14.0.dev0"
-}

model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c4ccda95a16eb6f3ab02aa574946b01870f16a4af0da6bdb5afaa962e4d9f0d9
-size 2519855456

preprocessor_config.json

@@ -1,13 +0,0 @@
-{
-  "feature_extractor_type": "NeuCodecFeatureExtractor",
-  "feature_size": 80,
-  "frame_length": 400,
-  "frame_shift": 160,
-  "hop_length": 320,
-  "num_mel_bins": 80,
-  "padding_side": "right",
-  "padding_value": 1,
-  "return_attention_mask": true,
-  "sampling_rate": 16000,
-  "stride": 2
-}