ready for training

README.md

@@ -1,57 +0,0 @@
----
-license: apache-2.0
-tags:
-- generated_from_trainer
-datasets:
-- common_voice
-model-index:
-- name: ''
-  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. -->
-
-# 
-
-This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the common_voice dataset.
-
-## 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: 0.0003
-- train_batch_size: 16
-- eval_batch_size: 8
-- seed: 42
-- 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
-- num_epochs: 15.0
-- mixed_precision_training: Native AMP
-
-### Training results
-
-
-
-### Framework versions
-
-- Transformers 4.22.0.dev0
-- Pytorch 1.11.0+cu113
-- Datasets 2.4.0
-- Tokenizers 0.12.1

added_tokens.json

@@ -1,4 +0,0 @@
-{
-  "</s>": 47,
-  "<s>": 46
-}

all_results.json

@@ -1,14 +0,0 @@
-{
-    "epoch": 15.0,
-    "eval_loss": 19.86508560180664,
-    "eval_runtime": 0.4623,
-    "eval_samples": 9,
-    "eval_samples_per_second": 19.467,
-    "eval_steps_per_second": 4.326,
-    "eval_wer": 1.0,
-    "train_loss": 24.409126790364585,
-    "train_runtime": 20.8017,
-    "train_samples": 22,
-    "train_samples_per_second": 15.864,
-    "train_steps_per_second": 0.721
-}

config.json

@@ -1,117 +0,0 @@
-{
-  "_name_or_path": "facebook/wav2vec2-base",
-  "activation_dropout": 0.0,
-  "adapter_kernel_size": 3,
-  "adapter_stride": 2,
-  "add_adapter": false,
-  "apply_spec_augment": true,
-  "architectures": [
-    "Wav2Vec2ForCTC"
-  ],
-  "attention_dropout": 0.0,
-  "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": 0.0,
-  "feat_quantizer_dropout": 0.0,
-  "final_dropout": 0.0,
-  "freeze_feat_extract_train": true,
-  "hidden_act": "gelu",
-  "hidden_dropout": 0.0,
-  "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": 45,
-  "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": "4.22.0.dev0",
-  "use_weighted_layer_sum": false,
-  "vocab_size": 48,
-  "xvector_output_dim": 512
-}

eval_results.json

@@ -1,9 +0,0 @@
-{
-    "epoch": 15.0,
-    "eval_loss": 19.86508560180664,
-    "eval_runtime": 0.4623,
-    "eval_samples": 9,
-    "eval_samples_per_second": 19.467,
-    "eval_steps_per_second": 4.326,
-    "eval_wer": 1.0
-}

preprocessor_config.json

@@ -1,9 +0,0 @@
-{
-  "do_normalize": true,
-  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
-  "feature_size": 1,
-  "padding_side": "right",
-  "padding_value": 0.0,
-  "return_attention_mask": false,
-  "sampling_rate": 16000
-}

pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b7020e5b6d127c2a75362883d75ca0d7ddafb6744cd555006ae55e73c762ae60
-size 377706071

run.sh

@@ -1,23 +1,28 @@
 #!/usr/bin/env bash
 CUDA_VISIBLE_DEVICES="0" python run_speech_recognition_ctc.py \
-	--dataset_name="common_voice" \
-	--model_name_or_path="facebook/wav2vec2-base" \
-	--dataset_config_name="ab" \
+	--dataset_name="/home/patrick_huggingface_co/ami-kaldi-chunked-wav2vec2-base" \
+	--model_name_or_path="facebook/wav2vec2-large-lv60" \
+	--dataset_config_name="ihm" \
+	--train_split_name="train" \
+	--eval_split_name="validation" \
 	--output_dir="./" \
+	--preprocessing_num_workers="16" \
 	--overwrite_output_dir \
-	--num_train_epochs="15" \
+	--num_train_epochs="3" \
 	--per_device_train_batch_size="32" \
+	--gradient_accumulation_steps="1" \
 	--learning_rate="3e-4" \
 	--warmup_steps="500" \
 	--evaluation_strategy="steps" \
-	--text_column_name="sentence" \
-	--length_column_name="input_length" \
+	--text_column_name="text" \
 	--save_steps="400" \
 	--eval_steps="100" \
+	--logging_steps="1" \
 	--layerdrop="0.0" \
 	--save_total_limit="3" \
-	--freeze_feature_encoder \
+	--freeze_feature_extractor \
 	--gradient_checkpointing \
+	--chars_to_ignore , ? . ! - \; \: \" “ % ‘ ” \
 	--fp16 \
 	--group_by_length \
 	--push_to_hub \

special_tokens_map.json

@@ -1,22 +0,0 @@
-{
-  "additional_special_tokens": [
-    {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false
-    }
-  ],
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "pad_token": "[PAD]",
-  "unk_token": "[UNK]"
-}

tokenizer_config.json

@@ -1,12 +0,0 @@
-{
-  "bos_token": "<s>",
-  "do_lower_case": false,
-  "eos_token": "</s>",
-  "name_or_path": "./",
-  "pad_token": "[PAD]",
-  "replace_word_delimiter_char": " ",
-  "special_tokens_map_file": null,
-  "tokenizer_class": "Wav2Vec2CTCTokenizer",
-  "unk_token": "[UNK]",
-  "word_delimiter_token": "|"
-}

train_results.json

@@ -1,8 +0,0 @@
-{
-    "epoch": 15.0,
-    "train_loss": 24.409126790364585,
-    "train_runtime": 20.8017,
-    "train_samples": 22,
-    "train_samples_per_second": 15.864,
-    "train_steps_per_second": 0.721
-}

trainer_state.json

@@ -1,25 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 15.0,
-  "global_step": 15,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 15.0,
-      "step": 15,
-      "total_flos": 2.629133656215552e+16,
-      "train_loss": 24.409126790364585,
-      "train_runtime": 20.8017,
-      "train_samples_per_second": 15.864,
-      "train_steps_per_second": 0.721
-    }
-  ],
-  "max_steps": 15,
-  "num_train_epochs": 15,
-  "total_flos": 2.629133656215552e+16,
-  "trial_name": null,
-  "trial_params": null
-}

training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0a609728264d711b88677fd490926ca3e18b3681ec912259bcc35a92d12c4366
-size 3311

vocab.json

@@ -1,48 +0,0 @@
-{
-  "!": 1,
-  ",": 2,
-  "-": 3,
-  ".": 4,
-  ":": 5,
-  "?": 6,
-  "[PAD]": 45,
-  "[UNK]": 44,
-  "|": 0,
-  "а": 7,
-  "б": 8,
-  "в": 9,
-  "г": 10,
-  "д": 11,
-  "е": 12,
-  "ж": 13,
-  "з": 14,
-  "и": 15,
-  "к": 16,
-  "л": 17,
-  "м": 18,
-  "н": 19,
-  "о": 20,
-  "п": 21,
-  "р": 22,
-  "с": 23,
-  "т": 24,
-  "у": 25,
-  "ф": 26,
-  "х": 27,
-  "ц": 28,
-  "ш": 29,
-  "ы": 30,
-  "ь": 31,
-  "қ": 32,
-  "ҟ": 33,
-  "ҩ": 34,
-  "ҭ": 35,
-  "ҳ": 36,
-  "ҵ": 37,
-  "ҽ": 38,
-  "ҿ": 39,
-  "ә": 40,
-  "ӡ": 41,
-  "ӷ": 42,
-  "ԥ": 43
-}