From b7cb19b01a1454f7a1388e24dcd4e10fc654bd7c Mon Sep 17 00:00:00 2001
From: shixian.shi <shixian.shi@alibaba-inc.com>
Date: 星期二, 16 一月 2024 11:30:25 +0800
Subject: [PATCH] update demo, readme
---
README.md | 30 ++++++++++++++++--------------
1 files changed, 16 insertions(+), 14 deletions(-)
diff --git a/README.md b/README.md
index 05f6364..2bd28e2 100644
--- a/README.md
+++ b/README.md
@@ -61,7 +61,6 @@
| paraformer-zh-spk <br> ( [猸怾(https://modelscope.cn/models/damo/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn/summary) [馃]() ) | speech recognition with speaker diarization, with timestamps, non-streaming | 60000 hours, Mandarin | 220M |
| <nobr>paraformer-zh-online <br> ( [猸怾(https://modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary) [馃]() )</nobr> | speech recognition, streaming | 60000 hours, Mandarin | 220M |
| paraformer-en <br> ( [猸怾(https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-en-16k-common-vocab10020/summary) [馃]() ) | speech recognition, with timestamps, non-streaming | 50000 hours, English | 220M |
-| paraformer-en-spk <br> ([猸怾()[馃]() ) | speech recognition with speaker diarization, non-streaming | Undo | Undo |
| conformer-en <br> ( [猸怾(https://modelscope.cn/models/damo/speech_conformer_asr-en-16k-vocab4199-pytorch/summary) [馃]() ) | speech recognition, non-streaming | 50000 hours, English | 220M |
| ct-punc <br> ( [猸怾(https://modelscope.cn/models/damo/punc_ct-transformer_cn-en-common-vocab471067-large/summary) [馃]() ) | punctuation restoration | 100M, Mandarin and English | 1.1G |
| fsmn-vad <br> ( [猸怾(https://modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary) [馃]() ) | voice activity detection | 5000 hours, Mandarin and English | 0.4M |
@@ -96,9 +95,9 @@
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")
-res = model(input=f"{model.model_path}/example/asr_example.wav",
- batch_size=16,
- hotword='榄旀惌')
+res = model.generate(input=f"{model.model_path}/example/asr_example.wav",
+ batch_size=64,
+ hotword='榄旀惌')
print(res)
```
Note: `model_hub`: represents the model repository, `ms` stands for selecting ModelScope download, `hf` stands for selecting Huggingface download.
@@ -125,7 +124,7 @@
for i in range(total_chunk_num):
speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride]
is_final = i == total_chunk_num - 1
- res = model(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size, encoder_chunk_look_back=encoder_chunk_look_back, decoder_chunk_look_back=decoder_chunk_look_back)
+ res = model.generate(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size, encoder_chunk_look_back=encoder_chunk_look_back, decoder_chunk_look_back=decoder_chunk_look_back)
print(res)
```
Note: `chunk_size` is the configuration for streaming latency.` [0,10,5]` indicates that the real-time display granularity is `10*60=600ms`, and the lookahead information is `5*60=300ms`. Each inference input is `600ms` (sample points are `16000*0.6=960`), and the output is the corresponding text. For the last speech segment input, `is_final=True` needs to be set to force the output of the last word.
@@ -135,9 +134,8 @@
from funasr import AutoModel
model = AutoModel(model="fsmn-vad", model_revision="v2.0.2")
-
wav_file = f"{model.model_path}/example/asr_example.wav"
-res = model(input=wav_file)
+res = model.generate(input=wav_file)
print(res)
```
### Voice Activity Detection (Non-streaming)
@@ -158,7 +156,7 @@
for i in range(total_chunk_num):
speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride]
is_final = i == total_chunk_num - 1
- res = model(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size)
+ res = model.generate(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size)
if len(res[0]["value"]):
print(res)
```
@@ -167,8 +165,7 @@
from funasr import AutoModel
model = AutoModel(model="ct-punc", model_revision="v2.0.2")
-
-res = model(input="閭ｄ粖澶╃殑浼氬氨鍒拌繖閲屽惂 happy new year 鏄庡勾瑙�")
+res = model.generate(input="閭ｄ粖澶╃殑浼氬氨鍒拌繖閲屽惂 happy new year 鏄庡勾瑙�")
print(res)
```
### Timestamp Prediction
@@ -176,10 +173,9 @@
from funasr import AutoModel
model = AutoModel(model="fa-zh", model_revision="v2.0.2")
-
wav_file = f"{model.model_path}/example/asr_example.wav"
-text_file = f"{model.model_path}/example/asr_example.wav"
-res = model(input=(wav_file, text_file), data_type=("sound", "text"))
+text_file = f"{model.model_path}/example/text.txt"
+res = model.generate(input=(wav_file, text_file), data_type=("sound", "text"))
print(res)
```
[//]: # (FunASR supports inference and fine-tuning of models trained on industrial datasets of tens of thousands of hours. For more details, please refer to ([modelscope_egs](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_pipeline/quick_start.html)). It also supports training and fine-tuning of models on academic standard datasets. For more details, please refer to([egs](https://alibaba-damo-academy.github.io/FunASR/en/academic_recipe/asr_recipe.html)). The models include speech recognition (ASR), speech activity detection (VAD), 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](https://github.com/alibaba-damo-academy/FunASR/blob/main/docs/model_zoo/modelscope_models.md):)
@@ -233,10 +229,16 @@
}
@inproceedings{gao22b_interspeech,
author={Zhifu Gao and ShiLiang Zhang and Ian McLoughlin and Zhijie Yan},
- title={{Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition}},
+ title={Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition},
year=2022,
booktitle={Proc. Interspeech 2022},
pages={2063--2067},
doi={10.21437/Interspeech.2022-9996}
}
+@inproceedings{shi2023seaco,
+ author={Xian Shi and Yexin Yang and Zerui Li and Yanni Chen and Zhifu Gao and Shiliang Zhang},
+ title={SeACo-Paraformer: A Non-Autoregressive ASR System with Flexible and Effective Hotword Customization Ability},
+ year={2023},
+ booktitle={ICASSP2024}
+}
```
--
Gitblit v1.9.1