add readme file

.ipynb_checkpoints/added_tokens-checkpoint.json

@@ -1 +0,0 @@
-{"<s>": 42, "</s>": 43}

.ipynb_checkpoints/config-checkpoint.json

@@ -1,108 +0,0 @@
-{
-  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
-  "activation_dropout": 0.0,
-  "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": 768,
-  "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": 0.0,
-  "feat_quantizer_dropout": 0.0,
-  "final_dropout": 0.0,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout": 0.1,
-  "hidden_size": 1024,
-  "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "layer_norm_eps": 1e-05,
-  "layerdrop": 0.0,
-  "mask_feature_length": 64,
-  "mask_feature_min_masks": 0,
-  "mask_feature_prob": 0.25,
-  "mask_time_length": 10,
-  "mask_time_min_masks": 2,
-  "mask_time_prob": 0.75,
-  "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": 41,
-  "proj_codevector_dim": 768,
-  "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": "4.17.0.dev0",
-  "use_weighted_layer_sum": false,
-  "vocab_size": 44,
-  "xvector_output_dim": 512
-}

.ipynb_checkpoints/preprocessor_config-checkpoint.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": true,
-  "sampling_rate": 16000
-}

.ipynb_checkpoints/special_tokens_map-checkpoint.json

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

.ipynb_checkpoints/tokenizer_config-checkpoint.json

@@ -1 +0,0 @@
-{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "/workspace/container_0/model/", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

.ipynb_checkpoints/vocab-checkpoint.json

@@ -1 +0,0 @@
-{"aa": 1, "ae": 2, "ah": 3, "aw": 4, "ay": 5, "b": 6, "ch": 7, "d": 8, "dh": 9, "dx": 10, "eh": 11, "er": 12, "ey": 13, "f": 14, "g": 15, "h#": 16, "hh": 17, "ih": 18, "iy": 19, "jh": 20, "k": 21, "l": 22, "m": 23, "n": 24, "ng": 25, "ow": 26, "oy": 27, "p": 28, "r": 29, "s": 30, "sh": 31, "t": 32, "th": 33, "uh": 34, "uw": 35, "v": 36, "w": 37, "y": 38, "z": 39, "|": 0, "[UNK]": 40, "[PAD]": 41}

README.md

@@ -0,0 +1,57 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- automatic-speech-recognition
+- pytorch
+- transformers
+- en
+- generated_from_trainer
+model-index:
+- name: model
+  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. -->
+
+# model
+
+This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the Timit 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: 3e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- 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: 2000
+- training_steps: 10000
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- Transformers 4.17.0.dev0
+- Pytorch 1.10.2+cu102
+- Datasets 1.18.2.dev0
+- Tokenizers 0.11.0

vocab.json

@@ -1 +1 @@
-{"\u0251": 1, "\u00e6": 2, "\u0259": 3, "a\u028a": 4, "a\u026a": 5, "b": 6, "\u02a7": 7, "d": 8, "\u00f0": 9, "dx": 10, "\u025b": 11, "\u0259r": 12, "e\u026a": 13, "f": 14, "g": 15, "": 16, "h": 17, "\u026a": 18, "i": 19, "\u02a4": 20, "k": 21, "l": 22, "m": 23, "n": 24, "\u014b": 25, "o\u028a": 26, "\u0254\u026a": 27, "p": 28, "r": 29, "s": 30, "\u0283": 31, "t": 32, "\u03b8": 33, "\u028a": 34, "u": 35, "v": 36, "w": 37, "j": 38, "z": 39, "|": 0, "[UNK]": 40, "[PAD]": 41}
+{"\u0251": 1, "\u00e6": 2, "\u0259": 3, "a\u028a": 4, "a\u026a": 5, "b": 6, "\u02a7": 7, "d": 8, "\u00f0": 9, "dx": 10, "\u025b": 11, "\u0259r": 12, "e\u026a": 13, "f": 14, "g": 15, " ": 16, "h": 17, "\u026a": 18, "i": 19, "\u02a4": 20, "k": 21, "l": 22, "m": 23, "n": 24, "\u014b": 25, "o\u028a": 26, "\u0254\u026a": 27, "p": 28, "r": 29, "s": 30, "\u0283": 31, "t": 32, "\u03b8": 33, "\u028a": 34, "u": 35, "v": 36, "w": 37, "j": 38, "z": 39, "|": 0, "[UNK]": 40, "[PAD]": 41}