Update README.md
Browse files
README.md
CHANGED
|
@@ -3,6 +3,8 @@ tags:
|
|
| 3 |
- espnet
|
| 4 |
- audio
|
| 5 |
- audio-to-audio
|
|
|
|
|
|
|
| 6 |
language: en
|
| 7 |
license: cc-by-4.0
|
| 8 |
---
|
|
@@ -11,7 +13,7 @@ license: cc-by-4.0
|
|
| 11 |
|
| 12 |
### `wyz/vctk_bsrnn_xtiny_causal`
|
| 13 |
|
| 14 |
-
This model was trained by
|
| 15 |
|
| 16 |
### Demo: How to use in ESPnet2
|
| 17 |
|
|
@@ -32,8 +34,8 @@ model = SeparateSpeech.from_pretrained(
|
|
| 32 |
)
|
| 33 |
# For loading a downloaded model
|
| 34 |
# model = SeparateSpeech(
|
| 35 |
-
# train_config="exp_vctk/
|
| 36 |
-
# model_file="exp_vctk/
|
| 37 |
# normalize_output_wav=True,
|
| 38 |
# device="cuda",
|
| 39 |
# )
|
|
@@ -43,6 +45,37 @@ enhanced = model(audio[None, :], fs=fs)[0]
|
|
| 43 |
```
|
| 44 |
|
| 45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
|
| 47 |
## ENH config
|
| 48 |
|
|
|
|
| 3 |
- espnet
|
| 4 |
- audio
|
| 5 |
- audio-to-audio
|
| 6 |
+
datasets:
|
| 7 |
+
- VCTK_DEMAND
|
| 8 |
language: en
|
| 9 |
license: cc-by-4.0
|
| 10 |
---
|
|
|
|
| 13 |
|
| 14 |
### `wyz/vctk_bsrnn_xtiny_causal`
|
| 15 |
|
| 16 |
+
This model was trained by wyz based on the universal_se_v1 recipe in [espnet](https://github.com/espnet/espnet/).
|
| 17 |
|
| 18 |
### Demo: How to use in ESPnet2
|
| 19 |
|
|
|
|
| 34 |
)
|
| 35 |
# For loading a downloaded model
|
| 36 |
# model = SeparateSpeech(
|
| 37 |
+
# train_config="exp_vctk/enh_train_enh_bsrnn_xtiny_raw/config.yaml",
|
| 38 |
+
# model_file="exp_vctk/enh_train_enh_bsrnn_xtiny_raw/xxxx.pth",
|
| 39 |
# normalize_output_wav=True,
|
| 40 |
# device="cuda",
|
| 41 |
# )
|
|
|
|
| 45 |
```
|
| 46 |
|
| 47 |
|
| 48 |
+
<!-- Generated by ./scripts/utils/show_enh_score.sh -->
|
| 49 |
+
# RESULTS
|
| 50 |
+
## Environments
|
| 51 |
+
- date: `Wed Feb 28 17:03:08 EST 2024`
|
| 52 |
+
- python version: `3.8.16 (default, Mar 2 2023, 03:21:46) [GCC 11.2.0]`
|
| 53 |
+
- espnet version: `espnet 202304`
|
| 54 |
+
- pytorch version: `pytorch 2.0.1+cu118`
|
| 55 |
+
- Git hash: `443028662106472c60fe8bd892cb277e5b488651`
|
| 56 |
+
- Commit date: `Thu May 11 03:32:59 2023 +0000`
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
## enhanced_test_16k
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
|dataset|PESQ_WB|STOI|SAR|SDR|SIR|SI_SNR|OVRL|SIG|BAK|P808_MOS|
|
| 63 |
+
|---|---|---|---|---|---|---|---|---|---|---|
|
| 64 |
+
|chime4_et05_real_isolated_6ch_track|1.13|45.98|-3.95|-3.95|0.00|-31.48|2.11|2.50|3.22|2.98|
|
| 65 |
+
|chime4_et05_simu_isolated_6ch_track|1.18|69.00|4.82|4.82|0.00|-0.29|2.03|2.36|3.37|2.66|
|
| 66 |
+
|dns20_tt_synthetic_no_reverb|1.99|92.09|13.16|13.16|0.00|12.77|2.87|3.40|3.45|3.57|
|
| 67 |
+
|reverb_et_real_8ch_multich|1.24|76.05|7.81|7.81|0.00|4.59|2.35|2.73|3.49|3.35|
|
| 68 |
+
|reverb_et_simu_8ch_multich|1.65|85.35|9.36|9.36|0.00|-10.50|2.79|3.24|3.57|3.60|
|
| 69 |
+
|whamr_tt_mix_single_reverb_max_16k|1.20|74.30|3.81|3.81|0.00|-0.21|2.04|2.37|3.36|3.02|
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
## enhanced_test_48k
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
|dataset|STOI|SAR|SDR|SIR|SI_SNR|OVRL|SIG|BAK|P808_MOS|
|
| 76 |
+
|---|---|---|---|---|---|---|---|---|---|
|
| 77 |
+
|vctk_noisy_tt_2spk|93.55|19.34|19.34|0.00|18.24|3.01|3.36|3.86|3.40|
|
| 78 |
+
|
| 79 |
|
| 80 |
## ENH config
|
| 81 |
|