jackoyoungblood commited on
Commit
2670ca5
1 Parent(s): df6395b

End of training

Browse files
Files changed (2) hide show
  1. README.md +17 -19
  2. generation_config.json +2 -2
README.md CHANGED
@@ -1,42 +1,40 @@
1
  ---
2
- language:
3
- - dv
4
  license: apache-2.0
5
- base_model: openai/whisper-small
6
  tags:
7
  - generated_from_trainer
8
  datasets:
9
- - mozilla-foundation/common_voice_13_0
10
  metrics:
11
  - wer
12
  model-index:
13
- - name: Whisper Small Dv - Sanchit Gandhi
14
  results:
15
  - task:
16
  name: Automatic Speech Recognition
17
  type: automatic-speech-recognition
18
  dataset:
19
- name: Common Voice 13
20
- type: mozilla-foundation/common_voice_13_0
21
- config: dv
22
- split: test
23
- args: dv
24
  metrics:
25
  - name: Wer
26
  type: wer
27
- value: 13.024654866641166
28
  ---
29
 
30
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
31
  should probably proofread and complete it, then remove this comment. -->
32
 
33
- # Whisper Small Dv - Sanchit Gandhi
34
 
35
- This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 13 dataset.
36
  It achieves the following results on the evaluation set:
37
- - Loss: 0.1698
38
- - Wer Ortho: 61.7522
39
- - Wer: 13.0247
40
 
41
  ## Model description
42
 
@@ -66,9 +64,9 @@ The following hyperparameters were used during training:
66
 
67
  ### Training results
68
 
69
- | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
70
- |:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
71
- | 0.1226 | 1.63 | 500 | 0.1698 | 61.7522 | 13.0247 |
72
 
73
 
74
  ### Framework versions
 
1
  ---
 
 
2
  license: apache-2.0
3
+ base_model: openai/whisper-tiny
4
  tags:
5
  - generated_from_trainer
6
  datasets:
7
+ - PolyAI/minds14
8
  metrics:
9
  - wer
10
  model-index:
11
+ - name: whisper-small-dv
12
  results:
13
  - task:
14
  name: Automatic Speech Recognition
15
  type: automatic-speech-recognition
16
  dataset:
17
+ name: PolyAI/minds14
18
+ type: PolyAI/minds14
19
+ config: en-US
20
+ split: train
21
+ args: en-US
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 0.0
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
  should probably proofread and complete it, then remove this comment. -->
30
 
31
+ # whisper-small-dv
32
 
33
+ This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.0004
36
+ - Wer Ortho: 0.0
37
+ - Wer: 0.0
38
 
39
  ## Model description
40
 
 
64
 
65
  ### Training results
66
 
67
+ | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
68
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:---:|
69
+ | 0.0014 | 13.89 | 500 | 0.0004 | 0.0 | 0.0 |
70
 
71
 
72
  ### Framework versions
generation_config.json CHANGED
@@ -51,7 +51,7 @@
51
  "forced_decoder_ids": [
52
  [
53
  1,
54
- 50322
55
  ],
56
  [
57
  2,
@@ -164,7 +164,7 @@
164
  "<|yo|>": 50325,
165
  "<|zh|>": 50260
166
  },
167
- "language": "sinhalese",
168
  "max_initial_timestamp_index": 1,
169
  "max_length": 448,
170
  "no_timestamps_token_id": 50363,
 
51
  "forced_decoder_ids": [
52
  [
53
  1,
54
+ 50259
55
  ],
56
  [
57
  2,
 
164
  "<|yo|>": 50325,
165
  "<|zh|>": 50260
166
  },
167
+ "language": "english",
168
  "max_initial_timestamp_index": 1,
169
  "max_length": 448,
170
  "no_timestamps_token_id": 50363,