Upload TextToAudioPipeline

README.md

@@ -1,7 +1,7 @@
 ---
-license: afl-3.0
 language:
 - ar
+license: afl-3.0
 pipeline_tag: text-to-speech
 ---
 # Model Card for Model ID

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<unk>": 39
+}

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "asg2024/vits-ar",
+  "_name_or_path": "/content/drive/MyDrive/vitsM/TO/TRUBO/haba/v1/fine2",
   "activation_dropout": 0.1,
   "architectures": [
     "VitsModel"
@@ -52,7 +52,7 @@
   "noise_scale_duration": 0.8,
   "num_attention_heads": 2,
   "num_hidden_layers": 6,
-  "num_speakers": 4,
+  "num_speakers": 1,
   "posterior_encoder_num_wavenet_layers": 16,
   "prior_encoder_num_flows": 4,
   "prior_encoder_num_wavenet_layers": 4,
@@ -80,7 +80,7 @@
   ],
   "sampling_rate": 16000,
   "segment_size": 8192,
-  "speaker_embedding_size": 256,
+  "speaker_embedding_size": 0,
   "speaking_rate": 1.0,
   "spectrogram_bins": 513,
   "torch_dtype": "float32",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d121b47f4e9a07e8644d6fa3dd14bac04963740fd4f98f1947c492bb0740575c
-size 345572936
+oid sha256:9b189c6905b693f87fc83aebcadaf9709bfb80eb985464a88731c3bb5a9c6d51
+size 145231480

tokenizer_config.json

@@ -1,5 +1,23 @@
 {
   "add_blank": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "ا",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "39": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
   "clean_up_tokenization_spaces": true,
   "is_uroman": false,
   "language": "ara",