benghoula
/

mms_tn

Model card Files Files and versions

benghoula commited on Aug 21, 2024

Commit

1616725

·

verified ·

1 Parent(s): a5f0e9f

Upload model

Files changed (2) hide show

config.json +5 -4
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -1,7 +1,8 @@
 {
   "activation_dropout": 0.1,
   "architectures": [
-    "VitsModelForPreTraining"
   ],
   "attention_dropout": 0.1,
   "depth_separable_channels": 2,
@@ -51,7 +52,7 @@
   "noise_scale_duration": 0.8,
   "num_attention_heads": 2,
   "num_hidden_layers": 6,
-  "num_speakers": 1,
   "posterior_encoder_num_wavenet_layers": 16,
   "prior_encoder_num_flows": 4,
   "prior_encoder_num_wavenet_layers": 4,
@@ -79,11 +80,11 @@
   ],
   "sampling_rate": 16000,
   "segment_size": 8192,
-  "speaker_embedding_size": 0,
   "speaking_rate": 1.0,
   "spectrogram_bins": 513,
   "torch_dtype": "float32",
-  "transformers_version": "4.43.3",
   "upsample_initial_channel": 512,
   "upsample_kernel_sizes": [
     16,

 {
+  "_name_or_path": "/home/adem/finetuned_tts_tn",
   "activation_dropout": 0.1,
   "architectures": [
+    "VitsModel"
   ],
   "attention_dropout": 0.1,
   "depth_separable_channels": 2,
   "noise_scale_duration": 0.8,
   "num_attention_heads": 2,
   "num_hidden_layers": 6,
+  "num_speakers": 8,
   "posterior_encoder_num_wavenet_layers": 16,
   "prior_encoder_num_flows": 4,
   "prior_encoder_num_wavenet_layers": 4,
   ],
   "sampling_rate": 16000,
   "segment_size": 8192,
+  "speaker_embedding_size": 256,
   "speaking_rate": 1.0,
   "spectrogram_bins": 513,
   "torch_dtype": "float32",
+  "transformers_version": "4.35.1",
   "upsample_initial_channel": 512,
   "upsample_kernel_sizes": [
     16,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0428f1a559b9eb1140f27dafb70b52964bf54eea7dee78cbf575f1db73fb306d
-size 332161480

 version https://git-lfs.github.com/spec/v1
+oid sha256:af1d78e621e71416a1241b32bd65221a0889c57bcbf53943e69314dc6ca733a5
+size 158647032