Training in progress, step 100

README.md

@@ -0,0 +1,80 @@
+---
+license: apache-2.0
+base_model: facebook/wav2vec2-base-960h
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: 240803_02-wav2vec2-ASR-Global-All-Clients
+  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. -->
+
+# 240803_02-wav2vec2-ASR-Global-All-Clients
+
+This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1602.1385
+- Wer: 0.5
+
+## 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: 0.0001
+- train_batch_size: 5
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 30
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Wer    |
+|:-------------:|:-------:|:----:|:---------------:|:------:|
+| No log        | 1.5625  | 100  | 1651.1355       | 0.5455 |
+| No log        | 3.125   | 200  | 1907.2052       | 0.6591 |
+| No log        | 4.6875  | 300  | 1935.7844       | 0.5909 |
+| No log        | 6.25    | 400  | 1993.4489       | 0.6705 |
+| 887.5139      | 7.8125  | 500  | 2107.5054       | 0.6136 |
+| 887.5139      | 9.375   | 600  | 2071.6125       | 0.6477 |
+| 887.5139      | 10.9375 | 700  | 1669.5919       | 0.7614 |
+| 887.5139      | 12.5    | 800  | 1577.1571       | 0.7045 |
+| 887.5139      | 14.0625 | 900  | 1514.3473       | 0.7273 |
+| 888.0898      | 15.625  | 1000 | 1421.1171       | 0.6477 |
+| 888.0898      | 17.1875 | 1100 | 1776.2109       | 0.6023 |
+| 888.0898      | 18.75   | 1200 | 1521.8093       | 0.6023 |
+| 888.0898      | 20.3125 | 1300 | 1656.8542       | 0.5682 |
+| 888.0898      | 21.875  | 1400 | 1542.9061       | 0.5795 |
+| 707.5553      | 23.4375 | 1500 | 1532.5880       | 0.5795 |
+| 707.5553      | 25.0    | 1600 | 1566.5312       | 0.5795 |
+| 707.5553      | 26.5625 | 1700 | 1591.6229       | 0.5227 |
+| 707.5553      | 28.125  | 1800 | 1512.0585       | 0.5114 |
+| 707.5553      | 29.6875 | 1900 | 1602.1385       | 0.5    |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,118 @@
+{
+  "_name_or_path": "240803_01-wav2vec2-ASR-Global-All-Clients",
+  "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": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "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": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "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": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "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_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "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": 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": 12,
+  "num_negatives": 100,
+  "output_hidden_size": 768,
+  "pad_token_id": 25,
+  "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": "4.42.4",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27959c5f0a0fc923fe0ee0ecc6b484f1d5f6769468cbcc573f75ea8c6e0fc7cb
+size 377611120

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2b736b319c4b6163487e6aa4782969b162728d50b09e7d332d88769d495ced3
+size 5112