End of training

README.md

@@ -0,0 +1,60 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+model-index:
+- name: eval_transliterated
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# eval_transliterated
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 2.2188
+- eval_model_preparation_time: 0.0054
+- eval_cer: 0.3354
+- eval_wer: 0.4724
+- eval_runtime: 31.1696
+- eval_samples_per_second: 18.351
+- eval_steps_per_second: 1.155
+- step: 0
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0006
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 300
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- training_steps: 1000
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.4.0
+- Datasets 2.20.0
+- Tokenizers 0.20.1

all_results.json

@@ -0,0 +1,10 @@
+{
+    "eval_cer": 0.33544957921157537,
+    "eval_loss": 2.218759059906006,
+    "eval_model_preparation_time": 0.0054,
+    "eval_runtime": 31.1696,
+    "eval_samples": 572,
+    "eval_samples_per_second": 18.351,
+    "eval_steps_per_second": 1.155,
+    "eval_wer": 0.47242942811174493
+}

config.json

@@ -0,0 +1,109 @@
+{
+  "_name_or_path": "/scratch/elec/puhe/p/palp3/MUCS/indicwav2vec_outputs/pd_warmup_500/s300_shuff100",
+  "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.3,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.3,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.2,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "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,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "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,
+  "output_hidden_size": 1024,
+  "pad_token_id": 148,
+  "proj_codevector_dim": 256,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 151,
+  "xvector_output_dim": 512
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "eval_cer": 0.33544957921157537,
+    "eval_loss": 2.218759059906006,
+    "eval_model_preparation_time": 0.0054,
+    "eval_runtime": 31.1696,
+    "eval_samples": 572,
+    "eval_samples_per_second": 18.351,
+    "eval_steps_per_second": 1.155,
+    "eval_wer": 0.47242942811174493
+}

json/default-b60d5edd0f197c71/0.0.0/7483f22a71512872c377524b97484f6d20c275799bb9e7cd8fb3198178d8220a/dataset_info.json

@@ -0,0 +1 @@
+{"description": "", "citation": "", "homepage": "", "license": "", "features": {"audio_id": {"dtype": "string", "_type": "Value"}, "audio_paths": {"dtype": "string", "_type": "Value"}, "transcriptions": {"dtype": "string", "_type": "Value"}}, "builder_name": "json", "dataset_name": "json", "config_name": "default", "version": {"version_str": "0.0.0", "major": 0, "minor": 0, "patch": 0}, "splits": {"train": {"name": "train", "num_bytes": 159776, "num_examples": 572, "dataset_name": "json"}}, "download_checksums": {"/m/triton/scratch/elec/puhe/p/palp3/MUCS/mucs_language_segregated_data/MUCS_test_languagesep_data.json": {"num_bytes": 1275544, "checksum": null}}, "download_size": 1275544, "dataset_size": 159776, "size_in_bytes": 1435320}

json/default-b60d5edd0f197c71/0.0.0/7483f22a71512872c377524b97484f6d20c275799bb9e7cd8fb3198178d8220a/json-train.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f67abacdef72568fdccdc70e54cc80c5aca72a7c217cf5c533dcdd9be5ca20b5
+size 160568

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08de7da709cb1c87182ea525062fcd525beeade5ce32613467ec0bcc59e40f04
+size 1262426580

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:954d7a455e31bcebf83d96e44fe9e8f1ef759e4b68320f663497b83816219fe0
+size 5496