Upload folder using huggingface_hub

config.json

@@ -0,0 +1,51 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "VoiceEmbedder"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50256
+  ],
+  "bos_token_id": 50256,
+  "classifier_proj_size": 256,
+  "d_model": 384,
+  "decoder_attention_heads": 6,
+  "decoder_ffn_dim": 1536,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 4,
+  "decoder_start_token_id": 50257,
+  "dropout": 0.0,
+  "encoder_attention_heads": 6,
+  "encoder_ffn_dim": 1536,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 4,
+  "eos_token_id": 50256,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "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": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "voice_embedder",
+  "num_hidden_layers": 4,
+  "num_mel_bins": 80,
+  "pad_token_id": 50256,
+  "projector_dim": 256,
+  "scale_embedding": false,
+  "sequence_length": 1000,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865,
+  "whisper_model": "openai/whisper-base"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c308ad6cce350447b45e252775dd85a1c082a46f541ad77f9207dd6d8045de6
+size 81900880

preprocessor_config.json

@@ -0,0 +1,16 @@
+{
+  "feature_size": 80,
+  "sampling_rate": 16000,
+  "padding_value": 0.0,
+  "padding_side": "right",
+  "return_attention_mask": false,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "n_fft": 400,
+  "hop_length": 160,
+  "chunk_length": 30,
+  "dither": 0.0,
+  "sequence_length": 1000,
+  "processor_class": "VoiceEmbedderProcessor"
+}