End of training

README.md

@@ -1,6 +1,4 @@
 ---
-license: mit
-base_model: microsoft/speecht5_tts
 tags:
 - generated_from_trainer
 model-index:
@@ -13,9 +11,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # speechT5persian
 
-This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.4833
+This model was trained from scratch on an unknown dataset.
 
 ## Model description
 
@@ -35,32 +31,18 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 128
-- eval_batch_size: 1
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 256
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 8
+- num_epochs: 64
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch | Step   | Validation Loss |
-|:-------------:|:-----:|:------:|:---------------:|
-| 0.5445        | 1.0   | 25221  | 0.5218          |
-| 0.544         | 2.0   | 50442  | 0.5055          |
-| 0.5596        | 3.0   | 75663  | 0.4956          |
-| 0.5373        | 4.0   | 100884 | 0.4952          |
-| 0.5333        | 5.0   | 126105 | 0.4912          |
-| 0.4858        | 6.0   | 151326 | 0.4833          |
-
-
 ### Framework versions
 
-- Transformers 4.36.2
+- Transformers 4.37.0.dev0
 - Pytorch 2.0.0
 - Datasets 2.16.1
 - Tokenizers 0.15.0

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "microsoft/speecht5_tts",
+  "_name_or_path": "/kaggle/working/mohammadnpak/speechT5persian/checkpoint-13482/",
   "activation_dropout": 0.1,
   "apply_spec_augment": true,
   "architectures": [

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "max_length": 1876,
+  "pad_token_id": 1,
+  "transformers_version": "4.37.0.dev0"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53476f4f57cfd7ef558d2264deff8515cd988fd35ff2c3e04526f413f30b9256
+oid sha256:a748a30a5f5ff920a65e0f44b4f54d3c1ce30bef1717003a5f8188538544745e
 size 577789320

runs/Jan18_16-53-25_d089d394e77b/events.out.tfevents.1705596818.d089d394e77b.182.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27aba2b11d6712c791204f649169069d15f77538c78fc2135678eca6dff5c91c
-size 129565
+oid sha256:24043e62dea38f02a1197409906ad709e36ed9db6f529b088a6575fa688d7c39
+size 129919

runs/Jan18_23-47-36_7e59366c5ad5/events.out.tfevents.1705621695.7e59366c5ad5.142.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16ff001239645661383968dd70cf9853bbb8737d375b0f6f87990e0618a8b2ed
+size 6397

runs/Jan18_23-56-46_7e59366c5ad5/events.out.tfevents.1705622216.7e59366c5ad5.142.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b570da95a47f4fc91b92e6c5350e4b1ebf290406a2d8f87cd096209a5018dc6e
+size 6436

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b4b7d372450345f50f6b19b45b09fbca294d247eecfed054050f2a58c8aa319
+oid sha256:5f2ab397ec213bf36ae931060f1d16deb477d1579c5eea087ca89568d0aa6731
 size 4475