End of training

README.md

@@ -22,11 +22,19 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the glaswegian_tts_v0.1.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7169
+- Loss: 0.7308
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
 
 ## Training and evaluation data
 
-[Glaswegian audio clips](https://huggingface.co/datasets/divakaivan/glaswegian_audio) 90/10 train/test split
+More information needed
 
 ## Training procedure
 
@@ -42,12 +50,20 @@ The following hyperparameters were used during training:
 - 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: 2000
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch    | Step | Validation Loss |
+|:-------------:|:--------:|:----:|:---------------:|
+| 0.4163        | 222.2222 | 1000 | 0.7073          |
+| 0.3999        | 444.4444 | 2000 | 0.7308          |
+
+
 ### Framework versions
 
 - Transformers 4.42.0.dev0
-- Pytorch 2.2.1+cu121
+- Pytorch 2.3.0+cu121
 - Datasets 2.19.1
 - Tokenizers 0.19.1

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": "4.42.0.dev0"
+}

runs/May30_10-30-06_6aeb0f3ad249/events.out.tfevents.1717065013.6aeb0f3ad249.437.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6b2a25f645d3efe00ec9b00b8c6c02ac0dde5d796c5a18dad75a578ca145543
-size 15138
+oid sha256:11ffdc42eaec34b3b7f448b7efff8f660d55111d34b8cc9f86b2826bcd9a5706
+size 24203