From 977dc3eb9832f251676f2d908f3d5793ecc45270 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=B8=B8=E9=9B=81?= Date: Tue, 16 Jan 2024 13:53:47 +0800 Subject: [PATCH] docs --- README.md | 3 +++ README_zh.md | 2 +- examples/industrial_data_pretraining/emotion2vec/demo.py | 3 ++- 3 files changed, 6 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 2bd28e218..0094dc4d4 100644 --- a/README.md +++ b/README.md @@ -178,6 +178,9 @@ 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 ([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):) ## Deployment Service diff --git a/README_zh.md b/README_zh.md index dc2030222..57a6bbb21 100644 --- a/README_zh.md +++ b/README_zh.md @@ -182,7 +182,7 @@ text_file = f"{model.model_path}/example/text.txt" res = model.generate(input=(wav_file, text_file), data_type=("sound", "text")) print(res) ``` -更多详细用法（[示例](examples/industrial_data_pretraining)） +更多详细用法（[示例](https://github.com/alibaba-damo-academy/FunASR/tree/main/examples/industrial_data_pretraining)） diff --git a/examples/industrial_data_pretraining/emotion2vec/demo.py b/examples/industrial_data_pretraining/emotion2vec/demo.py index ea8da99dd..91d00aabc 100644 --- a/examples/industrial_data_pretraining/emotion2vec/demo.py +++ b/examples/industrial_data_pretraining/emotion2vec/demo.py @@ -7,5 +7,6 @@ from funasr import AutoModel model = AutoModel(model="damo/emotion2vec_base", model_revision="v2.0.1") -res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav", output_dir="./outputs") +wav_file = f"{model.model_path}/example/example/test.wav" +res = model.generate(wav_file, output_dir="./outputs", granularity="utterance") print(res) \ No newline at end of file