Training in progress, step 100

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Abdullah-Habib/urdu_speech_tt",
+  "_name_or_path": "microsoft/speecht5_tts",
   "activation_dropout": 0.1,
   "apply_spec_augment": true,
   "architectures": [
@@ -85,7 +85,7 @@
   "speech_decoder_prenet_layers": 2,
   "speech_decoder_prenet_units": 256,
   "torch_dtype": "float32",
-  "transformers_version": "4.31.0",
+  "transformers_version": "4.35.2",
   "use_cache": false,
   "use_guided_attention_loss": true,
   "vocab_size": 81

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed29532681c232c9ea521f5faa6fcdf2ee12067db419a6b35edfb75ee0e2e46b
+size 577789320

preprocessor_config.json

@@ -1,7 +1,7 @@
 {
   "do_normalize": false,
   "feature_extractor_type": "SpeechT5FeatureExtractor",
-  "feature_size": 80,
+  "feature_size": 1,
   "fmax": 7600,
   "fmin": 80,
   "frame_signal_scale": 1.0,

runs/Dec22_18-05-16_275ee2e43671/events.out.tfevents.1703268472.275ee2e43671.1112.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fc6ed688e2a2fadac327113ea9029a3b534c4d5d8f38ad6a1d25b3a3abca0e1
+size 6401

runs/Dec22_18-12-56_275ee2e43671/events.out.tfevents.1703268821.275ee2e43671.1112.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b38ad9f9cac6ebb670d2e8a22005f3735b0267063dc3a78f92f49094bc060972
+size 6974

tokenizer_config.json

@@ -1,8 +1,60 @@
 {
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "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,
   "eos_token": "</s>",
+  "mask_token": "<mask>",
   "model_max_length": 600,
+  "normalize": false,
   "pad_token": "<pad>",
   "processor_class": "SpeechT5Processor",
   "sp_model_kwargs": {},

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03bfa5e957ed3e66d431a2cbcd97f978db22ec2c0a2fb5e4368bb8817d246a13
-size 4155
+oid sha256:87541e1e3cb4449cd5125a4c7a311a39248f349588692e454ea0cc075bc371d7
+size 4728