BLakshmiVijay/wakeworddetector

README.md

@@ -1,8 +1,11 @@
 ---
 license: apache-2.0
-base_model: BLakshmiVijay/results
+base_model: facebook/wav2vec2-base
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
+- recall
 model-index:
 - name: results
   results: []
@@ -13,7 +16,16 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model is a fine-tuned version of [BLakshmiVijay/results](https://huggingface.co/BLakshmiVijay/results) on the None dataset.
+This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6945
+- Accuracy: 0.4694
+- F1score: 0.6
+- Recall: 0.8667
+- Tn: 7
+- Fp: 46
+- Fn: 6
+- Tp: 39
 
 ## Model description
 
@@ -32,13 +44,29 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-07
+- learning_rate: 1e-08
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 50
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1score | Recall | Tn | Fp | Fn | Tp |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:-------:|:------:|:--:|:--:|:--:|:--:|
+| No log        | 1.0   | 13   | 0.6945          | 0.4694   | 0.6     | 0.8667 | 7  | 46 | 6  | 39 |
+| No log        | 2.0   | 26   | 0.6945          | 0.4694   | 0.6     | 0.8667 | 7  | 46 | 6  | 39 |
+| No log        | 3.0   | 39   | 0.6945          | 0.4694   | 0.6     | 0.8667 | 7  | 46 | 6  | 39 |
+| No log        | 4.0   | 52   | 0.6945          | 0.4694   | 0.6     | 0.8667 | 7  | 46 | 6  | 39 |
+| No log        | 5.0   | 65   | 0.6945          | 0.4694   | 0.6     | 0.8667 | 7  | 46 | 6  | 39 |
+| No log        | 6.0   | 78   | 0.6945          | 0.4694   | 0.6     | 0.8667 | 7  | 46 | 6  | 39 |
+| No log        | 7.0   | 91   | 0.6945          | 0.4694   | 0.6     | 0.8667 | 7  | 46 | 6  | 39 |
+| No log        | 8.0   | 104  | 0.6945          | 0.4694   | 0.6     | 0.8667 | 7  | 46 | 6  | 39 |
+| No log        | 9.0   | 117  | 0.6945          | 0.4694   | 0.6     | 0.8667 | 7  | 46 | 6  | 39 |
+| No log        | 10.0  | 130  | 0.6945          | 0.4694   | 0.6     | 0.8667 | 7  | 46 | 6  | 39 |
+
 
 ### Framework versions
 

config.json

@@ -1,6 +1,6 @@
 {
-  "_name_or_path": "BLakshmiVijay/results",
-  "activation_dropout": 0.05,
+  "_name_or_path": "facebook/wav2vec2-base",
+  "activation_dropout": 0.0,
   "adapter_attn_dim": null,
   "adapter_kernel_size": 3,
   "adapter_stride": 2,
@@ -14,7 +14,7 @@
   "classifier_proj_size": 256,
   "codevector_dim": 256,
   "contrastive_logits_temperature": 0.1,
-  "conv_bias": true,
+  "conv_bias": false,
   "conv_dim": [
     512,
     512,
@@ -42,24 +42,24 @@
     2,
     2
   ],
-  "ctc_loss_reduction": "mean",
-  "ctc_zero_infinity": true,
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
   "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_proj_dropout": 0.05,
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
   "feat_quantizer_dropout": 0.0,
   "final_dropout": 0.0,
+  "freeze_feat_extract_train": true,
   "hidden_act": "gelu",
-  "hidden_dropout": 0.05,
-  "hidden_size": 1024,
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "layer_norm_eps": 1e-05,
-  "layerdrop": 0.05,
+  "layerdrop": 0.0,
   "mask_channel_length": 10,
   "mask_channel_min_space": 1,
   "mask_channel_other": 0.0,
@@ -75,16 +75,18 @@
   "mask_time_prob": 0.05,
   "mask_time_selection": "static",
   "model_type": "wav2vec2",
+  "no_mask_channel_overlap": false,
+  "no_mask_time_overlap": false,
   "num_adapter_layers": 3,
-  "num_attention_heads": 16,
+  "num_attention_heads": 12,
   "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_hidden_layers": 12,
   "num_negatives": 100,
-  "output_hidden_size": 1024,
+  "output_hidden_size": 768,
   "pad_token_id": 0,
   "proj_codevector_dim": 256,
   "tdnn_dilation": [
@@ -111,6 +113,6 @@
   "torch_dtype": "float32",
   "transformers_version": "4.42.4",
   "use_weighted_layer_sum": false,
-  "vocab_size": 33,
+  "vocab_size": 32,
   "xvector_output_dim": 512
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93f1482235568c2db2cc799fbe35d2b6fb99af05a7126298b2f148c29bcfafb5
-size 1262859296
+oid sha256:3dcef60e7a2acd0d09912b59b54f4f49a9fadcd20861e7fbdc5092f754431fc0
+size 378302360

preprocessor_config.json

@@ -5,6 +5,6 @@
   "padding_side": "right",
   "padding_value": 0.0,
   "processor_class": "Wav2Vec2Processor",
-  "return_attention_mask": true,
+  "return_attention_mask": false,
   "sampling_rate": 16000
 }

special_tokens_map.json

@@ -1,30 +1,6 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": true,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": true,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": true,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": true,
-    "single_word": false
-  }
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -36,11 +36,13 @@
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "do_lower_case": false,
+  "do_normalize": true,
   "eos_token": "</s>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "processor_class": "Wav2Vec2Processor",
   "replace_word_delimiter_char": " ",
+  "return_attention_mask": false,
   "target_lang": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",
   "unk_token": "<unk>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c00fcd9b1ac703cee4b892848aa55631bd712328c07c399e684f12e9daede178
+oid sha256:c03d98f6987a8d6701acd27e9c9c83ba343e7412c69eea86a5d825056b49589f
 size 5112

vocab.json

@@ -1,35 +1,34 @@
 {
-  "'": 5,
-  "-": 6,
+  "'": 27,
   "</s>": 2,
   "<pad>": 0,
   "<s>": 1,
   "<unk>": 3,
-  "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,
+  "A": 7,
+  "B": 24,
+  "C": 19,
+  "D": 14,
+  "E": 5,
+  "F": 20,
+  "G": 21,
+  "H": 11,
+  "I": 10,
+  "J": 29,
+  "K": 26,
+  "L": 15,
+  "M": 17,
+  "N": 9,
+  "O": 8,
+  "P": 23,
+  "Q": 30,
+  "R": 13,
+  "S": 12,
+  "T": 6,
+  "U": 16,
+  "V": 25,
+  "W": 18,
+  "X": 28,
+  "Y": 22,
+  "Z": 31,
   "|": 4
 }