| | |
|---|
| | | # MIT License (https://opensource.org/licenses/MIT) |
|---|
| | | |
|---|
| | | from funasr import AutoModel |
|---|
| | | wav_file = "/Users/zhifu/funasr_github/test_local/asr_example.wav" |
|---|
| | | chunk_size = 60000 # ms |
|---|
| | | model = AutoModel(model="/Users/zhifu/Downloads/modelscope_models/speech_fsmn_vad_zh-cn-16k-common-streaming", model_revision="v2.0.0") |
|---|
| | | wav_file = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example.wav" |
|---|
| | | |
|---|
| | | res = model(input=wav_file, |
|---|
| | | chunk_size=chunk_size, |
|---|
| | | ) |
|---|
| | | model = AutoModel(model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch") |
|---|
| | | |
|---|
| | | res = model.generate(input=wav_file) |
|---|
| | | print(res) |
|---|
| | | # [[beg1, end1], [beg2, end2], .., [begN, endN]] |
|---|
| | | # beg/end: ms |
|---|
| | | |
|---|
| | | |
|---|
| | | # |
|---|
| | | # import soundfile |
|---|
| | | # import os |
|---|
| | | # |
|---|
| | | # # wav_file = os.path.join(model.model_path, "example/vad_example.wav") |
|---|
| | | # speech, sample_rate = soundfile.read(wav_file) |
|---|
| | | # |
|---|
| | | # chunk_stride = int(chunk_size * 16000 / 1000) |
|---|
| | | # |
|---|
| | | # cache = {} |
|---|
| | | # |
|---|
| | | # for i in range(int(len((speech)-1)/chunk_stride+1)): |
|---|
| | | # speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride] |
|---|
| | | # is_final = i == int(len((speech)-1)/chunk_stride+1) |
|---|
| | | # res = model(input=speech_chunk, |
|---|
| | | # cache=cache, |
|---|
| | | # is_final=is_final, |
|---|
| | | # chunk_size=chunk_size, |
|---|
| | | # ) |
|---|
| | | # print(res) |
|---|
| | | |
|---|
| | | import soundfile |
|---|
| | | import os |
|---|
| | | |
|---|
| | | wav_file = os.path.join(model.model_path, "example/vad_example.wav") |
|---|
| | | speech, sample_rate = soundfile.read(wav_file) |
|---|
| | | |
|---|
| | | chunk_size = 200 # ms |
|---|
| | | chunk_stride = int(chunk_size * sample_rate / 1000) |
|---|
| | | |
|---|
| | | cache = {} |
|---|
| | | |
|---|
| | | total_chunk_num = int(len((speech)-1)/chunk_stride+1) |
|---|
| | | 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.generate(input=speech_chunk, |
|---|
| | | cache=cache, |
|---|
| | | is_final=is_final, |
|---|
| | | chunk_size=chunk_size, |
|---|
| | | disable_pbar=True, |
|---|
| | | ) |
|---|
| | | # print(res) |
|---|
| | | if len(res[0]["value"]): |
|---|
| | | print(res) |
|---|
| | | |
|---|
| | | |
|---|
| | | # 1. [[beg1, end1], [beg2, end2], .., [begN, endN]]; [[beg, end]]; [[beg1, end1], [beg2, end2]] |
|---|
| | | # 2. [[beg, -1]] |
|---|
| | | # 3. [[-1, end]] |
|---|
| | | # beg/end: ms |
|---|
