Add config data

README.md

@@ -0,0 +1,6 @@
+
+# Wav2vec2-Large-English
+
+Fine-tuned [facebook/wav2vec2-large](https://huggingface.co/facebook/wav2vec2-large) on English using the [Common Voice](https://huggingface.co/datasets/common_voice).
+When using this model, make sure that your speech input is sampled at 16kHz.
+

config.json

@@ -1,15 +1,13 @@
 {
-  "_name_or_path": "tanmayplanet32/english-model",
+  "_name_or_path": "facebook/wav2vec2-large",
   "activation_dropout": 0.05,
   "apply_spec_augment": true,
   "architectures": [
-    "Wav2Vec2ForSpeechClassification"
+    "Wav2Vec2ForCTC"
   ],
   "attention_dropout": 0.1,
   "bos_token_id": 1,
-  "codevector_dim": 256,
-  "contrastive_logits_temperature": 0.1,
-  "conv_bias": true,
+  "conv_bias": false,
   "conv_dim": [
     512,
     512,
@@ -39,64 +37,34 @@
   ],
   "ctc_loss_reduction": "mean",
   "ctc_zero_infinity": true,
-  "diversity_loss_weight": 0.1,
-  "do_stable_layer_norm": true,
+  "do_stable_layer_norm": false,
   "eos_token_id": 2,
   "feat_extract_activation": "gelu",
   "feat_extract_dropout": 0.0,
-  "feat_extract_norm": "layer",
+  "feat_extract_norm": "group",
   "feat_proj_dropout": 0.05,
-  "feat_quantizer_dropout": 0.0,
-  "final_dropout": 0.0,
-  "finetuning_task": "wav2vec2_clf",
+  "final_dropout": 0.1,
   "gradient_checkpointing": true,
   "hidden_act": "gelu",
   "hidden_dropout": 0.05,
+  "hidden_dropout_prob": 0.1,
   "hidden_size": 1024,
-  "id2label": {
-    "0": "anger",
-    "1": "disgust",
-    "2": "fear",
-    "3": "happiness",
-    "4": "sadness"
-  },
   "initializer_range": 0.02,
   "intermediate_size": 4096,
-  "label2id": {
-    "anger": 0,
-    "disgust": 1,
-    "fear": 2,
-    "happiness": 3,
-    "sadness": 4
-  },
   "layer_norm_eps": 1e-05,
   "layerdrop": 0.05,
-  "mask_channel_length": 10,
-  "mask_channel_min_space": 1,
-  "mask_channel_other": 0.0,
-  "mask_channel_prob": 0.0,
-  "mask_channel_selection": "static",
   "mask_feature_length": 10,
   "mask_feature_prob": 0.0,
   "mask_time_length": 10,
-  "mask_time_min_space": 1,
-  "mask_time_other": 0.0,
   "mask_time_prob": 0.05,
-  "mask_time_selection": "static",
   "model_type": "wav2vec2",
   "num_attention_heads": 16,
-  "num_codevector_groups": 2,
-  "num_codevectors_per_group": 320,
   "num_conv_pos_embedding_groups": 16,
   "num_conv_pos_embeddings": 128,
   "num_feat_extract_layers": 7,
   "num_hidden_layers": 24,
-  "num_negatives": 100,
   "pad_token_id": 0,
   "pooling_mode": "mean",
-  "problem_type": "single_label_classification",
-  "proj_codevector_dim": 256,
-  "torch_dtype": "float32",
-  "transformers_version": "4.10.0.dev0",
+  "transformers_version": "4.7.0.dev0",
   "vocab_size": 33
-}
+}

preprocessor_config.json

@@ -6,4 +6,4 @@
   "padding_value": 0.0,
   "return_attention_mask": true,
   "sampling_rate": 16000
-}
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef32d54a3ebc911d64e7a8b8d04896f0957bbab4e3da4c6c0ae42ab901d6e4e7
+size 1262022892

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

vocab.json

@@ -0,0 +1 @@
+{"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "|": 4, "'": 5, "-": 6, "A": 7, "B": 8, "C": 9, "D": 10, "E": 11, "F": 12, "G": 13, "H": 14, "I": 15, "J": 16, "K": 17, "L": 18, "M": 19, "N": 20, "O": 21, "P": 22, "Q": 23, "R": 24, "S": 25, "T": 26, "U": 27, "V": 28, "W": 29, "X": 30, "Y": 31, "Z": 32}