model upload v1

config.json

@@ -0,0 +1,76 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 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,
+  "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,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "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_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "num_attention_heads": 16,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "pad_token_id": 61,
+  "transformers_version": "4.5.0.dev0",
+  "vocab_size": 62
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 199.94,
+    "eval_loss": 1.0759512186050415,
+    "eval_mem_cpu_alloc_delta": 12901181,
+    "eval_mem_cpu_peaked_delta": 845619,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 1679536640,
+    "eval_runtime": 4.9907,
+    "eval_samples": 98,
+    "eval_samples_per_second": 19.637,
+    "eval_wer": 0.857916102841678
+}

preprocessor_config.json

@@ -0,0 +1,8 @@
+{
+  "do_normalize": true,
+  "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:f6226b196d9fcf107d2f6fee3df85a6df389e5813e8e617c997baab962532582
+size 1262188055

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}

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": "|"}

vocab.json

@@ -0,0 +1 @@
+{"ବ": 0, "ଜ": 1, "ଳ": 2, "ଉ": 3, "ଁ": 4, "ଅ": 5, "ଙ": 6, "ୂ": 7, "ଚ": 8, "ଥ": 9, "ା": 10, "ୈ": 11, "ଇ": 12, "ସ": 13, "ଛ": 14, "ଝ": 15, "ଟ": 16, "ଞ": 17, "ମ": 18, "ଲ": 19, "ଗ": 20, "କ": 21, "ୌ": 22, "େ": 23, "ଣ": 24, "ଡ": 25, "ଓ": 26, "ଷ": 27, "ଊ": 28, "ଘ": 29, "ଵ": 30, "ଖ": 31, "ୟ": 32, "ଠ": 33, "ଭ": 34, "ୃ": 35, "ତ": 36, "ଦ": 37, "ଧ": 38, "ହ": 39, "୍": 40, "ୋ": 41, "ୁ": 42, "ଫ": 43, "ଆ": 44, "ି": 45, "ୀ": 46, "ଈ": 47, "ଶ": 48, "ର": 49, "ପ": 50, "ନ": 51, "ଂ": 52, "଼": 53, "ଃ": 54, "ଯ": 55, "ଢ": 56, "ୱ": 57, "ଏ": 58, "|": 59, "[UNK]": 60, "[PAD]": 61}