End of training

README.md

@@ -3,23 +3,20 @@ library_name: transformers
 license: mit
 base_model: microsoft/speecht5_tts
 tags:
-- tts
 - generated_from_trainer
-datasets:
-- microsoft/speecht5_tts
 model-index:
-- name: SpeechT5 Technical English
+- name: speecht5_finetuned_meenakshi_hindiTTS
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# SpeechT5 Technical English
+# speecht5_finetuned_meenakshi_hindiTTS
 
-This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the TTS_English_Technical_data dataset.
+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: 0.5263
+- Loss: 0.6188
 
 ## Model description
 
@@ -38,32 +35,35 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
+- learning_rate: 1e-05
 - train_batch_size: 4
 - eval_batch_size: 2
 - seed: 42
 - gradient_accumulation_steps: 8
 - total_train_batch_size: 32
-- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 100
-- training_steps: 500
+- training_steps: 800
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 7.8452        | 0.4206 | 100  | 0.7427          |
-| 5.4461        | 0.8412 | 200  | 0.5996          |
-| 4.8237        | 1.2618 | 300  | 0.5638          |
-| 4.6385        | 1.6824 | 400  | 0.5402          |
-| 4.4832        | 2.1030 | 500  | 0.5263          |
+| 1.7715        | 0.2944 | 100  | 1.2450          |
+| 1.0063        | 0.5889 | 200  | 0.8130          |
+| 0.8207        | 0.8833 | 300  | 0.7140          |
+| 0.7584        | 1.1778 | 400  | 0.6656          |
+| 0.7303        | 1.4722 | 500  | 0.6443          |
+| 0.7156        | 1.7667 | 600  | 0.6361          |
+| 0.6937        | 2.0611 | 700  | 0.6176          |
+| 0.6855        | 2.3555 | 800  | 0.6188          |
 
 
 ### Framework versions
 
-- Transformers 4.46.0.dev0
-- Pytorch 2.4.1+cu121
+- Transformers 4.44.2
+- Pytorch 2.5.0+cu121
 - Datasets 3.0.2
-- Tokenizers 0.20.1
+- Tokenizers 0.19.1

generation_config.json

@@ -5,5 +5,5 @@
   "eos_token_id": 2,
   "max_length": 1876,
   "pad_token_id": 1,
-  "transformers_version": "4.46.0.dev0"
+  "transformers_version": "4.44.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ef8d86762450565c1a9b4c74cbb97830bd728b1c74b684b98c2a55ecd5731b7
+oid sha256:784549e3177e65b674d771921fc0f61f58980990c26532c14005d544af8c9d68
 size 577789320

runs/Oct24_09-00-48_2a8668ac24c1/events.out.tfevents.1729760464.2a8668ac24c1.208.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc48e90f9b94cfdd2d878467ded6680418a816eaa5b140bebb5e2bb6d21102d0
-size 15491
+oid sha256:dd0666467870c7d19be8036409d7b133c61cbaa364cfd6e7286e4849850ebb06
+size 15845