funasr1.0.2

游雁

2024-01-25 369382050bf71c249944545f009a29a8632fdda5

 README.md

@@ -55,16 +55,16 @@
(Note: 🤗 represents the Huggingface model zoo link, ⭐ represents the ModelScope model zoo link)


|                                                                             Model Name                                                                             |                                Task Details                                 |          Training Data           | Parameters |
|:------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------:|:--------------------------------:|:----------:|
|    paraformer-zh <br> ([⭐](https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary)  [🤗]() )    |             speech recognition, with timestamps, non-streaming              |      60000 hours, Mandarin       |    220M    |
|                paraformer-zh-spk <br> ( [⭐](https://modelscope.cn/models/damo/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn/summary)  [🤗]() )                | speech recognition with speaker diarization, with timestamps, non-streaming |      60000 hours, Mandarin       |    220M    |
| <nobr>paraformer-zh-online <br> ( [⭐](https://modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary) [🤗]() )</nobr> |                        speech recognition, streaming                        |      60000 hours, Mandarin       |    220M    |
|         paraformer-en <br> ( [⭐](https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-en-16k-common-vocab10020/summary) [🤗]() )         |             speech recognition, with timestamps, non-streaming              |       50000 hours, English       |    220M    |
|                     conformer-en <br> ( [⭐](https://modelscope.cn/models/damo/speech_conformer_asr-en-16k-vocab4199-pytorch/summary) [🤗]() )                      |                      speech recognition, non-streaming                      |       50000 hours, English       |    220M    |
|                     ct-punc <br> ( [⭐](https://modelscope.cn/models/damo/punc_ct-transformer_cn-en-common-vocab471067-large/summary) [🤗]() )                      |                           punctuation restoration                           |    100M, Mandarin and English    |    1.1G    | 
|                          fsmn-vad <br> ( [⭐](https://modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary) [🤗]() )                          |                          voice activity detection                           | 5000 hours, Mandarin and English |    0.4M    | 
|                          fa-zh <br> ( [⭐](https://modelscope.cn/models/damo/speech_timestamp_prediction-v1-16k-offline/summary) [🤗]() )                           |                            timestamp prediction                             |       5000 hours, Mandarin       |    38M     | 
|                                                                             Model Name                                                                             |                    Task Details                    |          Training Data           | Parameters |
|:------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:--------------------------------------------------:|:--------------------------------:|:----------:|
|    paraformer-zh <br> ([⭐](https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary)  [🤗]() )    | speech recognition, with timestamps, non-streaming |      60000 hours, Mandarin       |    220M    |
| <nobr>paraformer-zh-online <br> ( [⭐](https://modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary) [🤗]() )</nobr> |           speech recognition, streaming            |      60000 hours, Mandarin       |    220M    |
|         paraformer-en <br> ( [⭐](https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-en-16k-common-vocab10020/summary) [🤗]() )         | speech recognition, with timestamps, non-streaming |       50000 hours, English       |    220M    |
|                     conformer-en <br> ( [⭐](https://modelscope.cn/models/damo/speech_conformer_asr-en-16k-vocab4199-pytorch/summary) [🤗]() )                      |         speech recognition, non-streaming          |       50000 hours, English       |    220M    |
|                     ct-punc <br> ( [⭐](https://modelscope.cn/models/damo/punc_ct-transformer_cn-en-common-vocab471067-large/summary) [🤗]() )                      |              punctuation restoration               |    100M, Mandarin and English    |    1.1G    | 
|                          fsmn-vad <br> ( [⭐](https://modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary) [🤗]() )                          |              voice activity detection              | 5000 hours, Mandarin and English |    0.4M    | 
|                          fa-zh <br> ( [⭐](https://modelscope.cn/models/damo/speech_timestamp_prediction-v1-16k-offline/summary) [🤗]() )                           |                timestamp prediction                |       5000 hours, Mandarin       |    38M     | 
|                cam++ <br> ( [⭐](https://modelscope.cn/models/iic/speech_campplus_sv_zh-cn_16k-common/summary) [🤗]() )                                             |        speaker verification/diarization            |            5000 hours            |    7.2M    | 



@@ -91,12 +91,13 @@
from funasr import AutoModel
# paraformer-zh is a multi-functional asr model
# use vad, punc, spk or not as you need
model = AutoModel(model="paraformer-zh", model_revision="v2.0.2", \
                  vad_model="fsmn-vad", vad_model_revision="v2.0.2", \
                  punc_model="ct-punc-c", punc_model_revision="v2.0.2", \
                  spk_model="cam++", spk_model_revision="v2.0.2")
model = AutoModel(model="paraformer-zh", model_revision="v2.0.4",
                  vad_model="fsmn-vad", vad_model_revision="v2.0.4",
                  punc_model="ct-punc-c", punc_model_revision="v2.0.4",
                  # spk_model="cam++", spk_model_revision="v2.0.2",
                  )
res = model.generate(input=f"{model.model_path}/example/asr_example.wav", 
                     batch_size=64, 
                     batch_size_s=300, 
                     hotword='魔搭')
print(res)
```
@@ -110,7 +111,7 @@
encoder_chunk_look_back = 4 #number of chunks to lookback for encoder self-attention
decoder_chunk_look_back = 1 #number of encoder chunks to lookback for decoder cross-attention

model = AutoModel(model="paraformer-zh-streaming", model_revision="v2.0.2")
model = AutoModel(model="paraformer-zh-streaming", model_revision="v2.0.4")

import soundfile
import os
@@ -133,7 +134,7 @@
```python
from funasr import AutoModel

model = AutoModel(model="fsmn-vad", model_revision="v2.0.2")
model = AutoModel(model="fsmn-vad", model_revision="v2.0.4")
wav_file = f"{model.model_path}/example/asr_example.wav"
res = model.generate(input=wav_file)
print(res)
@@ -143,7 +144,7 @@
from funasr import AutoModel

chunk_size = 200 # ms
model = AutoModel(model="fsmn-vad", model_revision="v2.0.2")
model = AutoModel(model="fsmn-vad", model_revision="v2.0.4")

import soundfile

@@ -164,7 +165,7 @@
```python
from funasr import AutoModel

model = AutoModel(model="ct-punc", model_revision="v2.0.2")
model = AutoModel(model="ct-punc", model_revision="v2.0.4")
res = model.generate(input="那今天的会就到这里吧 happy new year 明年见")
print(res)
```
@@ -172,12 +173,15 @@
```python
from funasr import AutoModel

model = AutoModel(model="fa-zh", model_revision="v2.0.2")
model = AutoModel(model="fa-zh", model_revision="v2.0.4")
wav_file = f"{model.model_path}/example/asr_example.wav"
text_file = f"{model.model_path}/example/text.txt"
res = model.generate(input=(wav_file, text_file), data_type=("sound", "text"))
print(res)
```

More examples ref to [docs](https://github.com/alibaba-damo-academy/FunASR/tree/main/examples/industrial_data_pretraining)

[//]: # (FunASR supports inference and fine-tuning of models trained on industrial datasets of tens of thousands of hours. For more details, please refer to &#40;[modelscope_egs]&#40;https://alibaba-damo-academy.github.io/FunASR/en/modelscope_pipeline/quick_start.html&#41;&#41;. It also supports training and fine-tuning of models on academic standard datasets. For more details, please refer to&#40;[egs]&#40;https://alibaba-damo-academy.github.io/FunASR/en/academic_recipe/asr_recipe.html&#41;&#41;. The models include speech recognition &#40;ASR&#41;, speech activity detection &#40;VAD&#41;, punctuation recovery, language model, speaker verification, speaker separation, and multi-party conversation speech recognition. For a detailed list of models, please refer to the [Model Zoo]&#40;https://github.com/alibaba-damo-academy/FunASR/blob/main/docs/model_zoo/modelscope_models.md&#41;:)

## Deployment Service