hanasim commited on
Commit
d303d56
1 Parent(s): dbfa988

Model save

Browse files
README.md CHANGED
@@ -1,42 +1,39 @@
1
  ---
2
- language:
3
- - te
4
  license: apache-2.0
5
  base_model: openai/whisper-base
6
  tags:
7
- - whisper-event
8
  - generated_from_trainer
9
  datasets:
10
- - mozilla-foundation/common_voice_16_0
11
  metrics:
12
  - wer
13
  model-index:
14
- - name: Breeze DSW Telugu - base
15
  results:
16
  - task:
17
  name: Automatic Speech Recognition
18
  type: automatic-speech-recognition
19
  dataset:
20
- name: mozilla-foundation/common_voice_16_0 te
21
- type: mozilla-foundation/common_voice_16_0
22
  config: te
23
  split: test
24
  args: te
25
  metrics:
26
  - name: Wer
27
  type: wer
28
- value: 89.28571428571429
29
  ---
30
 
31
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
32
  should probably proofread and complete it, then remove this comment. -->
33
 
34
- # Breeze DSW Telugu - base
35
 
36
- This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the mozilla-foundation/common_voice_16_0 te dataset.
37
  It achieves the following results on the evaluation set:
38
- - Loss: 2.0469
39
- - Wer: 89.2857
40
 
41
  ## Model description
42
 
 
1
  ---
 
 
2
  license: apache-2.0
3
  base_model: openai/whisper-base
4
  tags:
 
5
  - generated_from_trainer
6
  datasets:
7
+ - common_voice_16_0
8
  metrics:
9
  - wer
10
  model-index:
11
+ - name: breeze-listen-dsw-base-te
12
  results:
13
  - task:
14
  name: Automatic Speech Recognition
15
  type: automatic-speech-recognition
16
  dataset:
17
+ name: common_voice_16_0
18
+ type: common_voice_16_0
19
  config: te
20
  split: test
21
  args: te
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 90.65934065934066
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
+ # breeze-listen-dsw-base-te
32
 
33
+ This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the common_voice_16_0 dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 2.2441
36
+ - Wer: 90.6593
37
 
38
  ## Model description
39
 
runs/Jan18_11-47-34_knight/events.out.tfevents.1705574914.knight.158764.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f9eb7841d8c649f0a5f56639261715140f6ee396a48f431eef48913e26ff7bf
3
+ size 5884
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0b2b0d69a88e33a57c9026f288e24b2bcb5b487d1b5364d642c95a31ddcc109
3
- size 6712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c39b692367f261d5c465387a375366919317aebd7878da60707426ab100d97d
3
+ size 6776