From 9512a406c6e061ab0dad6b15fd41dc6f72744827 Mon Sep 17 00:00:00 2001
From: Patrick von Platen <patrick.v.platen@gmail.com>
Date: Fri, 15 Oct 2021 09:09:48 +0000
Subject: [PATCH] up

---
 config.json              | 69 ++++++++++++++++++++++++++++++++++++++++
 preprocessor_config.json |  9 ++++++
 pytorch_model.bin        |  3 ++
 special_tokens_map.json  |  1 +
 tokenizer_config.json    |  1 +
 vocab.json               |  1 +
 6 files changed, 84 insertions(+)
 create mode 100644 config.json
 create mode 100644 preprocessor_config.json
 create mode 100644 pytorch_model.bin
 create mode 100644 special_tokens_map.json
 create mode 100644 tokenizer_config.json
 create mode 100644 vocab.json

diff --git a/config.json b/config.json
new file mode 100644
index 0000000..9efe0e9
--- /dev/null
+++ b/config.json
@@ -0,0 +1,69 @@
+{
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "UniSpeechForPreTraining"
+  ],
+  "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": [
+    32,
+    32,
+    32
+  ],
+  "conv_kernel": [
+    8,
+    8,
+    8
+  ],
+  "conv_stride": [
+    4,
+    4,
+    4
+  ],
+  "ctc_loss_reduction": "sum",
+  "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": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 16,
+  "initializer_range": 0.02,
+  "intermediate_size": 20,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_feature_length": 10,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_prob": 0.05,
+  "model_type": "unispeech",
+  "num_attention_heads": 2,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 2,
+  "num_conv_pos_embeddings": 16,
+  "num_ctc_classes": 80,
+  "num_feat_extract_layers": 3,
+  "num_hidden_layers": 4,
+  "num_negatives": 10,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 256,
+  "replace_prob": 0.5,
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}
diff --git a/preprocessor_config.json b/preprocessor_config.json
new file mode 100644
index 0000000..a0b7227
--- /dev/null
+++ b/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": false,
+  "sampling_rate": 16000
+}
diff --git a/pytorch_model.bin b/pytorch_model.bin
new file mode 100644
index 0000000..9c9004b
--- /dev/null
+++ b/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2643de148bfbb4889453163ff6aecd31f477e4a3afc71efcedf0d9f0c79021a
+size 841515
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000..25bc396
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
\ No newline at end of file
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..df3a3f7
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "return_attention_mask": false, "do_normalize": true, "model_max_length": 9223372036854775807, "special_tokens_map_file": "/home/lysandre/.cache/huggingface/transformers/208086b2429fa2ba5b196810c1bcd7d61e2c8d4afd65d05d0670096d735fd5bb.9d6cd81ef646692fb1c169a880161ea1cb95f49694f220aced9b704b457e51dd", "tokenizer_file": null, "name_or_path": "facebook/wav2vec2-base-960h", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
\ No newline at end of file
diff --git a/vocab.json b/vocab.json
new file mode 100644
index 0000000..88181b9
--- /dev/null
+++ b/vocab.json
@@ -0,0 +1 @@
+{"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "|": 4, "E": 5, "T": 6, "A": 7, "O": 8, "N": 9, "I": 10, "H": 11, "S": 12, "R": 13, "D": 14, "L": 15, "U": 16, "M": 17, "W": 18, "C": 19, "F": 20, "G": 21, "Y": 22, "P": 23, "B": 24, "V": 25, "K": 26, "'": 27, "X": 28, "J": 29, "Q": 30, "Z": 31}
\ No newline at end of file