poonehmousavi commited on
Commit
60829c3
1 Parent(s): 943b1c6

Upload 3 files

Browse files
Files changed (3) hide show
  1. config.json +3 -0
  2. example-mn.mp3 +0 -0
  3. hyperparams.yaml +77 -0
config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "speechbrain_interface": "WhisperASR"
3
+ }
example-mn.mp3 ADDED
Binary file (41.5 kB). View file
 
hyperparams.yaml ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # ################################
2
+ # Model: Whisper (Encoder-Decoder) + NLL
3
+ # Augmentation: TimeDomainSpecAugment
4
+ # Authors: Pooneh Mousavi 2022
5
+ # ################################
6
+
7
+
8
+ # URL for the biggest Fairseq english whisper model.
9
+ whisper_hub: openai/whisper-large-v2
10
+
11
+ # Normalize inputs with
12
+ # the same normalization done in the paper. Refer to Appendix C for further information.
13
+ normalized_transcripts: True
14
+
15
+
16
+ language: mongolian
17
+
18
+ auto_mix_prec: False
19
+ sample_rate: 16000
20
+
21
+ # These values are only used for the searchers.
22
+ # They needs to be hardcoded and should not be changed with Whisper.
23
+ # They are used as part of the searching process.
24
+ # The bos token of the searcher will be timestamp_index
25
+ # and will be concatenated with the bos, language and task tokens.
26
+ timestamp_index: 50363
27
+ eos_index: 50257
28
+ bos_index: 50258
29
+
30
+ # Decoding parameters
31
+ min_decode_ratio: 0.0
32
+ max_decode_ratio: 0.1
33
+ test_beam_size: 8
34
+
35
+ # Model parameters
36
+ freeze_whisper: True
37
+ freeze_encoder: True
38
+
39
+
40
+
41
+ whisper: !new:speechbrain.lobes.models.huggingface_whisper.HuggingFaceWhisper
42
+ source: !ref <whisper_hub>
43
+ freeze: !ref <freeze_whisper>
44
+ freeze_encoder: !ref <freeze_encoder>
45
+ save_path: whisper_checkpoints
46
+ encoder_only: False
47
+
48
+
49
+
50
+ decoder: !new:speechbrain.decoders.seq2seq.S2SWhisperGreedySearch
51
+ model: !ref <whisper>
52
+ bos_index: !ref <timestamp_index>
53
+ eos_index: !ref <eos_index>
54
+ min_decode_ratio: !ref <min_decode_ratio>
55
+ max_decode_ratio: !ref <max_decode_ratio>
56
+
57
+ # test_beam_searcher: !new:speechbrain.decoders.seq2seq.S2SWhisperBeamSearch
58
+ # module: [!ref <whisper>]
59
+ # bos_index: !ref <timestamp_index>
60
+ # eos_index: !ref <eos_index>
61
+ # min_decode_ratio: !ref <min_decode_ratio>
62
+ # max_decode_ratio: !ref <max_decode_ratio>
63
+ # beam_size: !ref <test_beam_size>
64
+
65
+
66
+
67
+
68
+
69
+ modules:
70
+ whisper: !ref <whisper>
71
+ decoder: !ref <decoder>
72
+
73
+
74
+ pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
75
+ loadables:
76
+ whisper: !ref <whisper>
77
+