Training in progress, step 100

added_tokens.json

@@ -1,3 +1,4 @@
 {
-  "<pad>": 86
+  "<ctc_blank>": 80,
+  "<mask>": 79
 }

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "MBZUAI/speecht5_tts_clartts_ar",
+  "_name_or_path": "microsoft/speecht5_tts",
   "activation_dropout": 0.1,
   "apply_spec_augment": true,
   "architectures": [
@@ -88,5 +88,5 @@
   "transformers_version": "4.46.2",
   "use_cache": false,
   "use_guided_attention_loss": true,
-  "vocab_size": 98
+  "vocab_size": 81
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b0b8be99a3bec8d64bd2fa404fbcbc6ef0bd77483d943e11c630eccddfe4d58
-size 577841544
+oid sha256:ea0c693889179d322dda90d65c790f0e2a4499bc6c14275ad2cf5aaaad217f1a
+size 577789320

runs/Nov28_09-06-15_7a4ec1f530db/events.out.tfevents.1732784927.7a4ec1f530db.2699.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a182f2fa6c99a6d74e1381cfa2b1ef150d73686ff73246bcb598bb9c4e4407d1
+size 7808

special_tokens_map.json

@@ -1,6 +1,13 @@
 {
   "bos_token": "<s>",
   "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "pad_token": "<pad>",
   "unk_token": "<unk>"
 }

spm_char.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f4b56b4bbf0637c59a5c9c8531362bf8ce2bcde4fcd28ce0a0ec26cdf70a905
-size 403344
+oid sha256:7fcc48f3e225f627b1641db410ceb0c8649bd2b0c982e150b03f8be3728ab560
+size 238473

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<unk>",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -9,7 +9,7 @@
       "special": true
     },
     "1": {
-      "content": "<s>",
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -24,19 +24,36 @@
       "single_word": false,
       "special": true
     },
-    "86": {
-      "content": "<pad>",
+    "3": {
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "79": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "80": {
+      "content": "<ctc_blank>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
     }
   },
   "bos_token": "<s>",
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "model_max_length": 1000000000000000019884624838656,
+  "mask_token": "<mask>",
+  "model_max_length": 600,
   "normalize": false,
   "pad_token": "<pad>",
   "processor_class": "SpeechT5Processor",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d51ebfa045b3caa80e71d24fae3f35b168fd644e327b60557aa05ff3bbdebcd
+oid sha256:4321b6a4a8ac72ed5f2c228ed25eda1a428b0f19496a943a7a499cea0e50c063
 size 5432