| | |
|---|
| | | speech_list.append(speech_i) |
|---|
| | | speech_lengths_list.append(speech_lengths_i) |
|---|
| | | |
|---|
| | | return speech_list, speech_lengths_list |
|---|
| | | return speech_list, speech_lengths_list |
|---|
| | | |
|---|
| | | def merge_vad(vad_result, max_length=15000): |
|---|
| | | new_result = [] |
|---|
| | | time_step = [t[0] for t in vad_result] + [t[1] for t in vad_result] |
|---|
| | | time_step = sorted(list(set(time_step))) |
|---|
| | | if len(time_step) == 0: |
|---|
| | | return [] |
|---|
| | | bg = 0 |
|---|
| | | for i in range(len(time_step)-1): |
|---|
| | | time = time_step[i] |
|---|
| | | if time_step[i+1] - bg < max_length: |
|---|
| | | continue |
|---|
| | | if time - bg < max_length * 1.5: |
|---|
| | | new_result.append([bg, time]) |
|---|
| | | else: |
|---|
| | | split_num = int(time - bg) // max_length + 1 |
|---|
| | | spl_l = int(time - bg) // split_num |
|---|
| | | for j in range(split_num): |
|---|
| | | new_result.append([bg + j*spl_l, bg + (j+1)*spl_l]) |
|---|
| | | bg = time |
|---|
| | | new_result.append([bg, time_step[-1]]) |
|---|
| | | return new_result |
|---|
| | | |
|---|
