first model version

config.json

@@ -0,0 +1,79 @@
+{
+  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.05,
+  "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": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.05,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.05,
+  "mask_feature_length": 10,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_prob": 0.05,
+  "model_type": "wav2vec2",
+  "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,
+  "pad_token_id": 62,
+  "proj_codevector_dim": 768,
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.5",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 63
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:290957abe490058a04ecbee6023850429b2307edeaae9817cba84dfffa8414fe
+size 2490576273

preprocessor_config.json

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

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:173f4a2d9b8e57bf6d75145778e1ede29c37caa3b71c0899bf587f831186f507
+size 1262181937

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bd23e74ae0c6110f6556ad0c63082363c0b77cb074967b0d979fc031ec52f16
+size 14567

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26993425a531e9811ab2ae9e8abd4b8203e39b31b8bb7e762a4040dafafa684f
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66ffa2a2fa95a847109fe6f244fd10bf51d01b33a97c32b05bcd4c40279832f7
+size 623

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51fde39526229033643115dd6824a29cde6e3bae02f823600c54ba4f95f18977
+size 2799

vocab.json

@@ -0,0 +1 @@
+{"'": 1, "A": 2, "B": 3, "C": 4, "D": 5, "E": 6, "F": 7, "G": 8, "H": 9, "I": 10, "J": 11, "K": 12, "L": 13, "M": 14, "N": 15, "O": 16, "P": 17, "Q": 18, "R": 19, "S": 20, "T": 21, "U": 22, "V": 23, "W": 24, "X": 25, "Y": 26, "Z": 27, "a": 28, "b": 29, "c": 30, "d": 31, "e": 32, "f": 33, "g": 34, "h": 35, "i": 36, "j": 37, "k": 38, "l": 39, "m": 40, "n": 41, "o": 42, "p": 43, "q": 44, "r": 45, "s": 46, "t": 47, "u": 48, "v": 49, "w": 50, "x": 51, "y": 52, "z": 53, "Ä": 54, "Ö": 55, "Ü": 56, "ß": 57, "ä": 58, "ö": 59, "ü": 60, "|": 0, "[UNK]": 61, "[PAD]": 62}