Merge pull request #404 from alibaba-damo-academy/main

zhifu gao

2023-04-23 d5784e3444ff891b92c681d866f1d527a25cb299

 docs/modelscope_models.md

@@ -1,4 +1,4 @@
# Pretrained models on ModelScope
# Pretrained Models on ModelScope

## Model License
-  Apache License 2.0
@@ -8,11 +8,12 @@

### Speech Recognition Models
#### Paraformer Models

|                                                                     Model Name                                                                     | Language |          Training Data           | Vocab Size | Parameter | Offline/Online | Notes                                                                                                                           |
|:--------------------------------------------------------------------------------------------------------------------------------------------------:|:--------:|:--------------------------------:|:----------:|:---------:|:--------------:|:--------------------------------------------------------------------------------------------------------------------------------|
|        [Paraformer-large](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary)        | CN & EN  | Alibaba Speech Data (60000hours) |    8404    |   220M    |    Offline     | Duration of input wav <= 20s                                                                                                    |
| [Paraformer-large-long](https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) | CN & EN  | Alibaba Speech Data (60000hours) |    8404    |   220M    |    Offline     | Which ould deal with arbitrary length input wav                                                                                 |
| [paraformer-large-contextual](https://www.modelscope.cn/models/damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/summary) | CN & EN  | Alibaba Speech Data (60000hours) |    8404    |   220M    |    Offline     | Which supports the hotword customization based on the incentive enhancement, and improves the recall and precision of hotwords. |
| [Paraformer-large-contextual](https://www.modelscope.cn/models/damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/summary) | CN & EN  | Alibaba Speech Data (60000hours) |    8404    |   220M    |    Offline     | Which supports the hotword customization based on the incentive enhancement, and improves the recall and precision of hotwords. |
|              [Paraformer](https://modelscope.cn/models/damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8358-tensorflow1/summary)              | CN & EN  | Alibaba Speech Data (50000hours) |    8358    |    68M    |    Offline     | Duration of input wav <= 20s                                                                                                    |
|          [Paraformer-online](https://modelscope.cn/models/damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8358-tensorflow1/summary)           | CN & EN  | Alibaba Speech Data (50000hours) |    8404    |    68M    |     Online     | Which could deal with streaming input                                                                                           |
|       [Paraformer-tiny](https://www.modelscope.cn/models/damo/speech_paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch/summary)       |    CN    |  Alibaba Speech Data (200hours)  |    544     |   5.2M    |    Offline     | Lightweight Paraformer model which supports Mandarin command words recognition                                                  |
@@ -23,6 +24,7 @@


#### UniASR Models

|                                                               Model Name                                                               | Language |          Training Data           | Vocab Size | Parameter | Offline/Online | Notes                                                                                                                           |
|:--------------------------------------------------------------------------------------------------------------------------------------:|:--------:|:--------------------------------:|:----------:|:---------:|:--------------:|:--------------------------------------------------------------------------------------------------------------------------------|
|       [UniASR](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-online/summary)        | CN & EN  | Alibaba Speech Data (60000hours) |    8358    |   100M    |     Online     | UniASR streaming offline unifying models                                                                                                    |
@@ -32,13 +34,24 @@
|       [UniASR Urdu](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-ur-16k-common-vocab877-pytorch/summary)                  |   Urdu   |  Alibaba Speech Data (? hours)   |    877     |    95M    |     Online     | UniASR streaming offline unifying models                                                                                                    |

#### Conformer Models
#### Paraformer Models

|                                                       Model Name                                                       | Language |     Training Data     | Vocab Size | Parameter | Offline/Online | Notes                                                                                                                           |
|:----------------------------------------------------------------------------------------------------------------------:|:--------:|:---------------------:|:----------:|:---------:|:--------------:|:--------------------------------------------------------------------------------------------------------------------------------|
| [Conformer](https://modelscope.cn/models/damo/speech_conformer_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch/summary)   |   CN     |  AISHELL (178hours)   |    4234    |    44M    |    Offline     | Duration of input wav <= 20s                                                                                                    |
| [Conformer](https://www.modelscope.cn/models/damo/speech_conformer_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch/summary)   |   CN     | AISHELL-2 (1000hours) |    5212    |    44M    |    Offline     | Duration of input wav <= 20s                                                                                                    |


#### RNN-T Models

### Multi-talker Speech Recognition Models

#### MFCCA Models

|                                                  Model Name                                                   | Language |               Training Data                | Vocab Size | Parameter | Offline/Online | Notes                                                                                                                           |
|:-------------------------------------------------------------------------------------------------------------:|:--------:|:------------------------------------------:|:----------:|:---------:|:--------------:|:--------------------------------------------------------------------------------------------------------------------------------|
| [MFCCA](https://www.modelscope.cn/models/NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/summary)    |   CN     | AliMeeting、AISHELL-4、Simudata (917hours)   |     4950   |    45M    |    Offline     | Duration of input wav <= 20s, channel of input wav <= 8 channel |



### Voice Activity Detection Models

@@ -62,14 +75,20 @@

### Speaker Verification Models

|                                                  Model Name                                                   |   Training Data   | Parameters | Vocab Size | Notes |
|                                                  Model Name                                                   |   Training Data   | Parameters | Number Speaker | Notes |
|:-------------------------------------------------------------------------------------------------------------:|:-----------------:|:----------:|:----------:|:------|
| [Xvector](https://www.modelscope.cn/models/damo/speech_xvector_sv-zh-cn-cnceleb-16k-spk3465-pytorch/summary) | CNCeleb (?hours)  |   17.5M    |    3465    |       |
| [Xvector](https://www.modelscope.cn/models/damo/speech_xvector_sv-en-us-callhome-8k-spk6135-pytorch/summary) | CallHome (?hours) |    61M     |    6135    |       |
| [Xvector](https://www.modelscope.cn/models/damo/speech_xvector_sv-zh-cn-cnceleb-16k-spk3465-pytorch/summary) | CNCeleb (1,200 hours)  |   17.5M    |    3465    |    Xvector, speaker verification, Chinese   |
| [Xvector](https://www.modelscope.cn/models/damo/speech_xvector_sv-en-us-callhome-8k-spk6135-pytorch/summary) | CallHome (60 hours) |    61M     |    6135    |   Xvector, speaker verification, English    |

### Speaker diarization Models
### Speaker Diarization Models

|                                                    Model Name                                                    |    Training Data    | Parameters | Notes |
|:----------------------------------------------------------------------------------------------------------------:|:-------------------:|:----------:|:------|
| [SOND](https://www.modelscope.cn/models/damo/speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch/summary) | AliMeeting (?hours) |   40.5M    |       |
| [SOND](https://www.modelscope.cn/models/damo/speech_diarization_sond-en-us-callhome-8k-n16k4-pytorch/summary)    |  CallHome (?hours)  |     12M     |       |
| [SOND](https://www.modelscope.cn/models/damo/speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch/summary) | AliMeeting (120 hours) |   40.5M    |    Speaker diarization, profiles and records, Chinese |
| [SOND](https://www.modelscope.cn/models/damo/speech_diarization_sond-en-us-callhome-8k-n16k4-pytorch/summary)    |  CallHome (60 hours)  |     12M     |    Speaker diarization, profiles and records, English   |

### Timestamp Prediction Models

|                                                    Model Name                                     |  Language  |    Training Data    | Parameters | Notes |
|:--------------------------------------------------------------------------------------------------:|:--------------:|:-------------------:|:----------:|:------|
| [TP-Aligner](https://modelscope.cn/models/damo/speech_timestamp_prediction-v1-16k-offline/summary) | CN | Alibaba Speech Data (50000hours) |   37.8M    |    Timestamp prediction, Mandarin, middle size |