dammyogt commited on
Commit
5b19258
1 Parent(s): 0829da4

End of training

Browse files
Files changed (3) hide show
  1. README.md +68 -0
  2. generation_config.json +9 -0
  3. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - ha
4
+ license: mit
5
+ base_model: microsoft/speecht5_tts
6
+ tags:
7
+ - hausa
8
+ - generated_from_trainer
9
+ datasets:
10
+ - mozilla-foundation/common_voice_8_0
11
+ model-index:
12
+ - name: SpeechT5 TTS Hausa
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # SpeechT5 TTS Hausa
20
+
21
+ This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the VoxPopuli dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.4720
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 1e-05
43
+ - train_batch_size: 16
44
+ - eval_batch_size: 8
45
+ - seed: 42
46
+ - gradient_accumulation_steps: 2
47
+ - total_train_batch_size: 32
48
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
+ - lr_scheduler_type: linear
50
+ - lr_scheduler_warmup_steps: 500
51
+ - training_steps: 4000
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss |
56
+ |:-------------:|:-----:|:----:|:---------------:|
57
+ | 0.5538 | 18.18 | 1000 | 0.4983 |
58
+ | 0.5153 | 36.36 | 2000 | 0.4791 |
59
+ | 0.4983 | 54.55 | 3000 | 0.4696 |
60
+ | 0.4974 | 72.73 | 4000 | 0.4720 |
61
+
62
+
63
+ ### Framework versions
64
+
65
+ - Transformers 4.33.0.dev0
66
+ - Pytorch 2.0.1+cu118
67
+ - Datasets 2.14.4
68
+ - Tokenizers 0.13.3
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "eos_token_id": 2,
6
+ "max_length": 1876,
7
+ "pad_token_id": 1,
8
+ "transformers_version": "4.33.0.dev0"
9
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f28b8243e2cdd249dacb34346a551f46a317913636b6ebdc25a275b868887579
3
  size 577878333
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:094164579a115868c5749cbe1d5c0c1f46f09af225051c5245b4b4b529515c5d
3
  size 577878333