| | |
|---|
| | | |
|---|
| | | from funasr import AutoModel |
|---|
| | | |
|---|
| | | model = AutoModel(model="damo/emotion2vec_base", model_revision="v2.0.1") |
|---|
| | | # model="iic/emotion2vec_base" |
|---|
| | | model = AutoModel(model="iic/emotion2vec_base_finetuned", |
|---|
| | | # vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch", |
|---|
| | | # vad_model_revision="master", |
|---|
| | | # vad_kwargs={"max_single_segment_time": 2000}, |
|---|
| | | ) |
|---|
| | | |
|---|
| | | res = model(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/test.wav" |
|---|
| | | res = model.generate(wav_file, output_dir="./outputs", granularity="utterance", extract_embedding=False) |
|---|
| | | print(res) |
|---|
