| | |
|---|
| | | speech_length = speech.shape[0] |
|---|
| | | |
|---|
| | | sample_offset = 0 |
|---|
| | | chunk_size = [0, 8, 4] #[5, 10, 5] 600ms, [8, 8, 4] 480ms |
|---|
| | | chunk_size = [0, 10, 5] #[0, 10, 5] 600ms, [0, 8, 4] 480ms |
|---|
| | | encoder_chunk_look_back = 4 #number of chunks to lookback for encoder self-attention |
|---|
| | | decoder_chunk_look_back = 1 #number of encoder chunks to lookback for decoder cross-attention |
|---|
| | | stride_size = chunk_size[1] * 960 |
|---|
| | | param_dict = {"cache": dict(), "is_final": False, "chunk_size": chunk_size, "encoder_chunk_look_back": 4, "decoder_chunk_look_back": 1} |
|---|
| | | param_dict = {"cache": dict(), "is_final": False, "chunk_size": chunk_size, |
|---|
| | | "encoder_chunk_look_back": encoder_chunk_look_back, "decoder_chunk_look_back": decoder_chunk_look_back} |
|---|
| | | final_result = "" |
|---|
| | | |
|---|
| | | for sample_offset in range(0, speech_length, min(stride_size, speech_length - sample_offset)): |
|---|
