Hugging Face's logo

lithish2602
/
speecht5_tts_ta

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Model card Files
xet
 Metrics Community
lithish2602 commited on
Commit
b0be447
·
verified ·
1 Parent(s): 1091a27

Model save

Browse files
Files changed (6) hide show
  1. README.md +5 -17
  2. config.json +1 -1
  3. generation_config.json +1 -1
  4. model.safetensors +1 -1
  5. runs/Feb11_10-22-02_4b6f221b5896/events.out.tfevents.1739269327.4b6f221b5896.1368.0 +3 -0
  6. training_args.bin +1 -1
README.md CHANGED
@@ -17,8 +17,6 @@ should probably proofread and complete it, then remove this comment. -->
17
  # speecht5_tts_ta
18
 
19
  This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the common_voice_17_0 dataset.
20
- It achieves the following results on the evaluation set:
21
- - Loss: 0.5678
22
 
23
  ## Model description
24
 
@@ -43,24 +41,14 @@ The following hyperparameters were used during training:
43
  - seed: 42
44
  - gradient_accumulation_steps: 2
45
  - total_train_batch_size: 32
46
- - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
  - lr_scheduler_type: linear
48
  - training_steps: 4000
49
  - mixed_precision_training: Native AMP
50
 
51
- ### Training results
52
-
53
- | Training Loss | Epoch | Step | Validation Loss |
54
- |:-------------:|:------:|:----:|:---------------:|
55
- | 0.3551 | 500.0 | 1000 | 0.4988 |
56
- | 0.3218 | 1000.0 | 2000 | 0.5528 |
57
- | 0.2891 | 1500.0 | 3000 | 0.5593 |
58
- | 0.282 | 2000.0 | 4000 | 0.5678 |
59
-
60
-
61
  ### Framework versions
62
 
63
- - Transformers 4.47.0.dev0
64
- - Pytorch 2.5.0+cu121
65
- - Datasets 3.1.0
66
- - Tokenizers 0.20.3
 
17
  # speecht5_tts_ta
18
 
19
  This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the common_voice_17_0 dataset.
 
 
20
 
21
  ## Model description
22
 
 
41
  - seed: 42
42
  - gradient_accumulation_steps: 2
43
  - total_train_batch_size: 32
44
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
  - lr_scheduler_type: linear
46
  - training_steps: 4000
47
  - mixed_precision_training: Native AMP
48
 
 
 
 
 
 
 
 
 
 
 
49
  ### Framework versions
50
 
51
+ - Transformers 4.49.0.dev0
52
+ - Pytorch 2.5.1+cu124
53
+ - Datasets 3.2.0
54
+ - Tokenizers 0.21.0
config.json CHANGED
@@ -85,7 +85,7 @@
85
  "speech_decoder_prenet_layers": 2,
86
  "speech_decoder_prenet_units": 256,
87
  "torch_dtype": "float32",
88
- "transformers_version": "4.47.0.dev0",
89
  "use_cache": false,
90
  "use_guided_attention_loss": true,
91
  "vocab_size": 81
 
85
  "speech_decoder_prenet_layers": 2,
86
  "speech_decoder_prenet_units": 256,
87
  "torch_dtype": "float32",
88
+ "transformers_version": "4.49.0.dev0",
89
  "use_cache": false,
90
  "use_guided_attention_loss": true,
91
  "vocab_size": 81
generation_config.json CHANGED
@@ -5,5 +5,5 @@
5
  "eos_token_id": 2,
6
  "max_length": 1876,
7
  "pad_token_id": 1,
8
- "transformers_version": "4.47.0.dev0"
9
  }
 
5
  "eos_token_id": 2,
6
  "max_length": 1876,
7
  "pad_token_id": 1,
8
+ "transformers_version": "4.49.0.dev0"
9
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8701b182ca42d029df5de43609a4969f1698e1c8ac3f6f9b8aca7ba5b4320e39
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4aa2e14cb30ee6eeb6441a5c4c44a7b2b65a661931fbdee5996f5965dffcc72a
3
  size 577789320
runs/Feb11_10-22-02_4b6f221b5896/events.out.tfevents.1739269327.4b6f221b5896.1368.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e0cabc66598bed92556d416bdb4466228d78f6c5d5fec5f5ee1d49c23109444
3
+ size 12571
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a7d68bfe83fdd11958091dd367d211be38d9588c541ebd38b576000f9f3f322
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84462e4208167c5f5263176908e29284dad7d5839f179e36454976c7db02817b
3
  size 5496