Upload processor

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+language_model/5gram_pa_3_correct.arpa filter=lfs diff=lfs merge=lfs -text
+language_model/unigrams.txt filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 68,
+  "<s>": 67
+}

alphabet.json

@@ -0,0 +1 @@
+{"labels": [" ", "\u0a02", "\u0a05", "\u0a06", "\u0a07", "\u0a08", "\u0a09", "\u0a0a", "\u0a0f", "\u0a10", "\u0a13", "\u0a14", "\u0a15", "\u0a16", "\u0a17", "\u0a18", "\u0a19", "\u0a1a", "\u0a1b", "\u0a1c", "\u0a1d", "\u0a1e", "\u0a1f", "\u0a20", "\u0a21", "\u0a22", "\u0a23", "\u0a24", "\u0a25", "\u0a26", "\u0a27", "\u0a28", "\u0a2a", "\u0a2b", "\u0a2c", "\u0a2d", "\u0a2e", "\u0a2f", "\u0a30", "\u0a32", "\u0a33", "\u0a35", "\u0a36", "\u0a38", "\u0a39", "\u0a3c", "\u0a3e", "\u0a3f", "\u0a40", "\u0a41", "\u0a42", "\u0a47", "\u0a48", "\u0a4b", "\u0a4c", "\u0a4d", "\u0a59", "\u0a5a", "\u0a5b", "\u0a5c", "\u0a5e", "\u0a70", "\u0a71", "\u0a72", "\u0a73", "\u2047", "", "<s>", "</s>"], "is_bpe": false}

language_model/5gram_pa_3_correct.arpa

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce972eb49510901ea96057ce1254e60e14574b2e247acd45417f6b939fda7fee
+size 3547686182

language_model/attrs.json

@@ -0,0 +1 @@
+{"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}

language_model/unigrams.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f772b807a5159fc0a3ec01f3d54981ff5f09bde6e26528578ad911500ec090d
+size 15788456

preprocessor_config.json

@@ -0,0 +1,11 @@
+{
+  "feature_extractor_type": "SeamlessM4TFeatureExtractor",
+  "feature_size": 80,
+  "num_mel_bins": 80,
+  "padding_side": "right",
+  "padding_value": 1,
+  "processor_class": "M4TProcessorWithLM",
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "stride": 2
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "65": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "66": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "67": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "68": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "M4TProcessorWithLM",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,69 @@
+{
+  "[PAD]": 66,
+  "[UNK]": 65,
+  "|": 0,
+  "ਂ": 1,
+  "ਅ": 2,
+  "ਆ": 3,
+  "ਇ": 4,
+  "ਈ": 5,
+  "ਉ": 6,
+  "ਊ": 7,
+  "ਏ": 8,
+  "ਐ": 9,
+  "ਓ": 10,
+  "ਔ": 11,
+  "ਕ": 12,
+  "ਖ": 13,
+  "ਗ": 14,
+  "ਘ": 15,
+  "ਙ": 16,
+  "ਚ": 17,
+  "ਛ": 18,
+  "ਜ": 19,
+  "ਝ": 20,
+  "ਞ": 21,
+  "ਟ": 22,
+  "ਠ": 23,
+  "ਡ": 24,
+  "ਢ": 25,
+  "ਣ": 26,
+  "ਤ": 27,
+  "ਥ": 28,
+  "ਦ": 29,
+  "ਧ": 30,
+  "ਨ": 31,
+  "ਪ": 32,
+  "ਫ": 33,
+  "ਬ": 34,
+  "ਭ": 35,
+  "ਮ": 36,
+  "ਯ": 37,
+  "ਰ": 38,
+  "ਲ": 39,
+  "ਲ਼": 40,
+  "ਵ": 41,
+  "ਸ਼": 42,
+  "ਸ": 43,
+  "ਹ": 44,
+  "਼": 45,
+  "ਾ": 46,
+  "ਿ": 47,
+  "ੀ": 48,
+  "ੁ": 49,
+  "ੂ": 50,
+  "ੇ": 51,
+  "ੈ": 52,
+  "ੋ": 53,
+  "ੌ": 54,
+  "੍": 55,
+  "ਖ਼": 56,
+  "ਗ਼": 57,
+  "ਜ਼": 58,
+  "ੜ": 59,
+  "ਫ਼": 60,
+  "ੰ": 61,
+  "ੱ": 62,
+  "ੲ": 63,
+  "ੳ": 64
+}