wyz commited on
Commit
ee8fce3
·
verified ·
1 Parent(s): cdbc190

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -19
README.md CHANGED
@@ -4,8 +4,6 @@ tags:
4
  - audio
5
  - audio-to-audio
6
  language: en
7
- datasets:
8
- - universal_se
9
  license: cc-by-4.0
10
  ---
11
 
@@ -13,7 +11,7 @@ license: cc-by-4.0
13
 
14
  ### `wyz/vctk_dns2020_whamr_bsrnn_large_noncausal`
15
 
16
- This model was trained by Emrys365 using universal_se recipe in [espnet](https://github.com/espnet/espnet/).
17
 
18
  ### Demo: How to use in ESPnet2
19
 
@@ -28,19 +26,19 @@ from espnet2.bin.enh_inference import SeparateSpeech
28
 
29
  # For model downloading + loading
30
  model = SeparateSpeech.from_pretrained(
31
- model_tag=wyz/vctk_dns2020_whamr_bsrnn_large_noncausal,
32
  normalize_output_wav=True,
33
- device=cuda,
34
  )
35
  # For loading a downloaded model
36
  # model = SeparateSpeech(
37
- # train_config=exp_vctk_dns20_whamr/enh_train_enh_bsrnn_large_noncausal_raw/config.yaml,
38
- # model_file=exp_vctk_dns20_whamr/enh_train_enh_bsrnn_large_noncausal_raw/xxxx.pth,
39
  # normalize_output_wav=True,
40
  # device=cuda,
41
  # )
42
 
43
- audio, fs = sf.read(/path/to/noisy/utt1.flac)
44
  enhanced = model(audio[None, :], fs=fs)[0]
45
  ```
46
 
@@ -67,17 +65,6 @@ enhanced = model(audio[None, :], fs=fs)[0]
67
  |reverb_et_simu_8ch_multich|2.29|94.59|10.87|10.87|0.00|-8.41|3.12|3.49|3.82|3.83|
68
  |whamr_tt_mix_single_reverb_max_16k|2.34|94.47|11.98|11.98|0.00|10.41|3.27|3.52|4.10|3.80|
69
 
70
- module
71
- <!-- Generated by ./scripts/utils/show_enh_score.sh -->
72
- # RESULTS
73
- ## Environments
74
- - date: `Thu Jan 11 22:52:46 EST 2024`
75
- - python version: `3.8.16 (default, Mar 2 2023, 03:21:46) [GCC 11.2.0]`
76
- - espnet version: `espnet 202304`
77
- - pytorch version: `pytorch 2.0.1+cu118`
78
- - Git hash: `443028662106472c60fe8bd892cb277e5b488651`
79
- - Commit date: `Thu May 11 03:32:59 2023 +0000`
80
-
81
 
82
  ## enhanced_test_48k
83
 
 
4
  - audio
5
  - audio-to-audio
6
  language: en
 
 
7
  license: cc-by-4.0
8
  ---
9
 
 
11
 
12
  ### `wyz/vctk_dns2020_whamr_bsrnn_large_noncausal`
13
 
14
+ This model was trained by Emrys365 based on the universal_se_v1 recipe in [espnet](https://github.com/espnet/espnet/).
15
 
16
  ### Demo: How to use in ESPnet2
17
 
 
26
 
27
  # For model downloading + loading
28
  model = SeparateSpeech.from_pretrained(
29
+ model_tag="wyz/vctk_dns2020_whamr_bsrnn_large_noncausal",
30
  normalize_output_wav=True,
31
+ device="cuda",
32
  )
33
  # For loading a downloaded model
34
  # model = SeparateSpeech(
35
+ # train_config="exp_vctk_dns20_whamr/enh_train_enh_bsrnn_large_noncausal_raw/config.yaml",
36
+ # model_file="exp_vctk_dns20_whamr/enh_train_enh_bsrnn_large_noncausal_raw/xxxx.pth",
37
  # normalize_output_wav=True,
38
  # device=cuda,
39
  # )
40
 
41
+ audio, fs = sf.read("/path/to/noisy/utt1.flac")
42
  enhanced = model(audio[None, :], fs=fs)[0]
43
  ```
44
 
 
65
  |reverb_et_simu_8ch_multich|2.29|94.59|10.87|10.87|0.00|-8.41|3.12|3.49|3.82|3.83|
66
  |whamr_tt_mix_single_reverb_max_16k|2.34|94.47|11.98|11.98|0.00|10.41|3.27|3.52|4.10|3.80|
67
 
 
 
 
 
 
 
 
 
 
 
 
68
 
69
  ## enhanced_test_48k
70