benchmark

游雁

2023-03-16 4827ea7f82b684aa5ba853193071b0ba713615a7

benchmark

 funasr/runtime/python/benchmark_onnx.md

File was renamed from funasr/runtime/python/README.md
@@ -2,7 +2,7 @@

(Note: The service has been fully warm up.)

 Intel(R) Xeon(R) Platinum 8369B CPU @ 2.90GHz   16core-32processor    with avx512_vnni
 ### Intel(R) Xeon(R) Platinum 8369B CPU @ 2.90GHz   16core-32processor    with avx512_vnni

| concurrent-tasks | processing time(s) |  RTF   | Speedup Rate |
|:----------------:|:------------------:|:------:|:------------:|
@@ -19,3 +19,17 @@
|  96 (onnx fp32)  |        151         | 0.0042 |    238.0     |
|  96 (onnx int8)  |         80         | 0.0022 |    452.0     |


### Intel(R) Xeon(R) Platinum 8269CY CPU @ 2.50GHz   16core-32processor    with avx512_vnni

| concurrent-tasks | processing time(s) |  RTF   | Speedup Rate |
|:----------------:|:------------------:|:------:|:------------:|
|  1 (onnx fp32)   |        2613        | 0.0724 |     13.8     |
|  1 (onnx int8)   |        1321        | 0.0366 |     22.4     |
|  32 (onnx fp32)  |        170         | 0.0047 |    212.7     |
|  32 (onnx int8)  |        89          | 0.0025 |    407.0     |
|  64 (onnx fp32)  |        166         | 0.0046 |    217.1     |
|  64 (onnx int8)  |         87         | 0.0024 |    414.7     |


### 

 funasr/runtime/python/libtorch/torch_paraformer/utils/compute_wer.py

New file
@@ -0,0 +1,157 @@
import os
import numpy as np
import sys

def compute_wer(ref_file,
                hyp_file,
                cer_detail_file):
    rst = {
        'Wrd': 0,
        'Corr': 0,
        'Ins': 0,
        'Del': 0,
        'Sub': 0,
        'Snt': 0,
        'Err': 0.0,
        'S.Err': 0.0,
        'wrong_words': 0,
        'wrong_sentences': 0
    }

    hyp_dict = {}
    ref_dict = {}
    with open(hyp_file, 'r') as hyp_reader:
        for line in hyp_reader:
            key = line.strip().split()[0]
            value = line.strip().split()[1:]
            hyp_dict[key] = value
    with open(ref_file, 'r') as ref_reader:
        for line in ref_reader:
            key = line.strip().split()[0]
            value = line.strip().split()[1:]
            ref_dict[key] = value

    cer_detail_writer = open(cer_detail_file, 'w')
    for hyp_key in hyp_dict:
        if hyp_key in ref_dict:
           out_item = compute_wer_by_line(hyp_dict[hyp_key], ref_dict[hyp_key])
           rst['Wrd'] += out_item['nwords']
           rst['Corr'] += out_item['cor']
           rst['wrong_words'] += out_item['wrong']
           rst['Ins'] += out_item['ins']
           rst['Del'] += out_item['del']
           rst['Sub'] += out_item['sub']
           rst['Snt'] += 1
           if out_item['wrong'] > 0:
               rst['wrong_sentences'] += 1
           cer_detail_writer.write(hyp_key + print_cer_detail(out_item) + '\n')
           cer_detail_writer.write("ref:" + '\t' + "".join(ref_dict[hyp_key]) + '\n')
           cer_detail_writer.write("hyp:" + '\t' + "".join(hyp_dict[hyp_key]) + '\n')

    if rst['Wrd'] > 0:
        rst['Err'] = round(rst['wrong_words'] * 100 / rst['Wrd'], 2)
    if rst['Snt'] > 0:
        rst['S.Err'] = round(rst['wrong_sentences'] * 100 / rst['Snt'], 2)

    cer_detail_writer.write('\n')
    cer_detail_writer.write("%WER " + str(rst['Err']) + " [ " + str(rst['wrong_words'])+ " / " + str(rst['Wrd']) +
                            ", " + str(rst['Ins']) + " ins, " + str(rst['Del']) + " del, " + str(rst['Sub']) + " sub ]" + '\n')
    cer_detail_writer.write("%SER " + str(rst['S.Err']) + " [ " + str(rst['wrong_sentences']) + " / " + str(rst['Snt']) + " ]" + '\n')
    cer_detail_writer.write("Scored " + str(len(hyp_dict)) + " sentences, " + str(len(hyp_dict) - rst['Snt']) + " not present in hyp." + '\n')

     
def compute_wer_by_line(hyp,
                        ref):
    hyp = list(map(lambda x: x.lower(), hyp))
    ref = list(map(lambda x: x.lower(), ref))

    len_hyp = len(hyp)
    len_ref = len(ref)

    cost_matrix = np.zeros((len_hyp + 1, len_ref + 1), dtype=np.int16)

    ops_matrix = np.zeros((len_hyp + 1, len_ref + 1), dtype=np.int8)

    for i in range(len_hyp + 1):
        cost_matrix[i][0] = i
    for j in range(len_ref + 1):
        cost_matrix[0][j] = j

    for i in range(1, len_hyp + 1):
        for j in range(1, len_ref + 1):
            if hyp[i - 1] == ref[j - 1]:
                cost_matrix[i][j] = cost_matrix[i - 1][j - 1]
            else:
                substitution = cost_matrix[i - 1][j - 1] + 1
                insertion = cost_matrix[i - 1][j] + 1
                deletion = cost_matrix[i][j - 1] + 1

                compare_val = [substitution, insertion, deletion]

                min_val = min(compare_val)
                operation_idx = compare_val.index(min_val) + 1
                cost_matrix[i][j] = min_val
                ops_matrix[i][j] = operation_idx

    match_idx = []
    i = len_hyp
    j = len_ref
    rst = {
        'nwords': len_ref,
        'cor': 0,
        'wrong': 0,
        'ins': 0,
        'del': 0,
        'sub': 0
    }
    while i >= 0 or j >= 0:
        i_idx = max(0, i)
        j_idx = max(0, j)

        if ops_matrix[i_idx][j_idx] == 0:  # correct
            if i - 1 >= 0 and j - 1 >= 0:
                match_idx.append((j - 1, i - 1))
                rst['cor'] += 1

            i -= 1
            j -= 1

        elif ops_matrix[i_idx][j_idx] == 2:  # insert
            i -= 1
            rst['ins'] += 1

        elif ops_matrix[i_idx][j_idx] == 3:  # delete
            j -= 1
            rst['del'] += 1

        elif ops_matrix[i_idx][j_idx] == 1:  # substitute
            i -= 1
            j -= 1
            rst['sub'] += 1

        if i < 0 and j >= 0:
            rst['del'] += 1
        elif j < 0 and i >= 0:
            rst['ins'] += 1

    match_idx.reverse()
    wrong_cnt = cost_matrix[len_hyp][len_ref]
    rst['wrong'] = wrong_cnt

    return rst

def print_cer_detail(rst):
    return ("(" + "nwords=" + str(rst['nwords']) + ",cor=" + str(rst['cor'])
            + ",ins=" + str(rst['ins']) + ",del=" + str(rst['del']) + ",sub="
            + str(rst['sub']) + ") corr:" + '{:.2%}'.format(rst['cor']/rst['nwords'])
            + ",cer:" + '{:.2%}'.format(rst['wrong']/rst['nwords']))

if __name__ == '__main__':
    if len(sys.argv) != 4:
        print("usage : python compute-wer.py test.ref test.hyp test.wer")
        sys.exit(0)

    ref_file = sys.argv[1]
    hyp_file = sys.argv[2]
    cer_detail_file = sys.argv[3]
    compute_wer(ref_file, hyp_file, cer_detail_file)