Upload SpeechToJyutpingPipeline

config.json

@@ -1,13 +1,5 @@
 {
   "_name_or_path": "hon9kon9ize/wav2vec2bert-jyutping",
-  "custom_pipelines": {
-    "speech-to-jyutping": {
-      "impl": "pipeline.SpeechToJyutpingPipeline",
-      "pt": [
-        "model.Wav2Vec2BertForCantonese"
-      ]
-    }
-  },
   "activation_dropout": 0.0,
   "adapter_act": "relu",
   "adapter_kernel_size": 3,
@@ -26,6 +18,14 @@
   "conv_depthwise_kernel_size": 31,
   "ctc_loss_reduction": "mean",
   "ctc_zero_infinity": false,
+  "custom_pipelines": {
+    "speech-to-jyutping": {
+      "impl": "hon9kon9ize/wav2vec2bert-jyutping--pipeline.SpeechToJyutpingPipeline",
+      "pt": [
+        "model.Wav2Vec2BertForCantonese"
+      ]
+    }
+  },
   "diversity_loss_weight": 0.1,
   "eos_token_id": 2,
   "feat_proj_dropout": 0.0,
@@ -83,7 +83,7 @@
   ],
   "tone_vocab_size": 11,
   "torch_dtype": "float32",
-  "transformers_version": "4.46.1",
+  "transformers_version": "4.49.0",
   "use_intermediate_ffn_before_adapter": false,
   "use_weighted_layer_sum": false,
   "vocab_size": 77,

special_tokens_map.json

@@ -1,6 +1,30 @@
 {
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "pad_token": "[PAD]",
-  "unk_token": "[UNK]"
+  "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

@@ -621,6 +621,7 @@
   "clean_up_tokenization_spaces": false,
   "do_lower_case": false,
   "eos_token": "</s>",
+  "extra_special_tokens": {},
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "processor_class": "Wav2Vec2BertProcessor",
@@ -629,4 +630,4 @@
   "tokenizer_class": "Wav2Vec2CTCTokenizer",
   "unk_token": "[UNK]",
   "word_delimiter_token": "|"
-}
+}