Model save

README.md

@@ -1,26 +1,23 @@
 ---
-language:
-- en
 license: mit
 base_model: microsoft/speecht5_tts
 tags:
-- en_accent,mozilla,t5,common_voice_1_0
 - generated_from_trainer
 datasets:
-- mozilla-foundation/common_voice_1_0
+- common_voice_1_0
 model-index:
-- name: SpeechT5 TTS English Accented
+- name: speecht5_tts
   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 TTS English Accented
+# speecht5_tts
 
-This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the Common Voice dataset.
+This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the common_voice_1_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4468
+- Loss: 0.6337
 
 ## Model description
 
@@ -47,18 +44,14 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
-- training_steps: 4000
+- training_steps: 100
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.5303        | 8.0   | 1000 | 0.4673          |
-| 0.5048        | 16.0  | 2000 | 0.4554          |
-| 0.4809        | 24.0  | 3000 | 0.4450          |
-| 0.4903        | 32.0  | 4000 | 0.4468          |
+| 0.7822        | 0.8   | 100  | 0.6337          |
 
 
 ### Framework versions