duwuonline commited on
Commit
625cd90
1 Parent(s): 849ea4a

End of training

Browse files
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
- license: cc-by-nc-4.0
3
- base_model: facebook/mms-tts-vie
4
  tags:
5
  - generated_from_trainer
6
  datasets:
@@ -15,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # speecht5_finetuned_voxpopuli_nl
17
 
18
- This model is a fine-tuned version of [facebook/mms-tts-vie](https://huggingface.co/facebook/mms-tts-vie) on the audiofolder dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 4.6235
21
 
22
  ## Model description
23
 
@@ -51,16 +51,16 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-----:|:----:|:---------------:|
54
- | No log | 10.0 | 10 | 5.4309 |
55
- | No log | 20.0 | 20 | 5.1375 |
56
- | 3.1586 | 30.0 | 30 | 4.9770 |
57
- | 3.1586 | 40.0 | 40 | 4.8637 |
58
- | 2.9299 | 50.0 | 50 | 4.7869 |
59
- | 2.9299 | 60.0 | 60 | 4.7277 |
60
- | 2.9299 | 70.0 | 70 | 4.6799 |
61
- | 2.8457 | 80.0 | 80 | 4.6510 |
62
- | 2.8457 | 90.0 | 90 | 4.6388 |
63
- | 2.8227 | 100.0 | 100 | 4.6235 |
64
 
65
 
66
  ### Framework versions
 
1
  ---
2
+ license: mit
3
+ base_model: microsoft/speecht5_tts
4
  tags:
5
  - generated_from_trainer
6
  datasets:
 
15
 
16
  # speecht5_finetuned_voxpopuli_nl
17
 
18
+ This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the audiofolder dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.7123
21
 
22
  ## Model description
23
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-----:|:----:|:---------------:|
54
+ | 0.3587 | 5.71 | 10 | 0.8407 |
55
+ | 0.3256 | 11.43 | 20 | 0.7593 |
56
+ | 0.3727 | 17.14 | 30 | 0.7535 |
57
+ | 0.3344 | 22.86 | 40 | 0.7342 |
58
+ | 0.3175 | 28.57 | 50 | 0.7242 |
59
+ | 0.3036 | 34.29 | 60 | 0.7320 |
60
+ | 0.2998 | 40.0 | 70 | 0.7248 |
61
+ | 0.2901 | 45.71 | 80 | 0.6993 |
62
+ | 0.317 | 51.43 | 90 | 0.7162 |
63
+ | 0.3195 | 57.14 | 100 | 0.7123 |
64
 
65
 
66
  ### Framework versions
generation_config.json CHANGED
@@ -3,6 +3,7 @@
3
  "bos_token_id": 0,
4
  "decoder_start_token_id": 2,
5
  "eos_token_id": 2,
 
6
  "pad_token_id": 1,
7
  "transformers_version": "4.35.2"
8
  }
 
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": "4.35.2"
9
  }
runs/Jan18_11-52-35_71565f425e09/events.out.tfevents.1705578756.71565f425e09.1122.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e5f2536707d975fc65ec4af5eabd95951df5ff9ac0ec45b5937c2cb15392fa2
3
- size 14169
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47b3fccdb042c8c9bd2c2eb7ca22e038c38219b8bb2cdd9da34aceb980aedd7d
3
+ size 16589