Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Enabling char_level and compute_CER for aishell recipe #1554

Merged
merged 2 commits into from
Mar 18, 2024
Merged
Show file tree
Hide file tree
Changes from 1 commit
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 6 additions & 2 deletions egs/aishell/ASR/conformer_ctc/decode.py
Original file line number Diff line number Diff line change
Expand Up @@ -419,7 +419,7 @@ def save_results(
for key, results in results_dict.items():
recog_path = params.exp_dir / f"recogs-{test_set_name}-{key}.txt"
results = sorted(results)
store_transcripts(filename=recog_path, texts=results)
store_transcripts(filename=recog_path, texts=results, char_level=True)
if enable_log:
logging.info(f"The transcripts are stored in {recog_path}")

Expand All @@ -432,7 +432,11 @@ def save_results(
results_char.append((res[0], list("".join(res[1])), list("".join(res[2]))))
with open(errs_filename, "w") as f:
wer = write_error_stats(
f, f"{test_set_name}-{key}", results_char, enable_log=enable_log
f,
f"{test_set_name}-{key}",
results_char,
enable_log=enable_log,
compute_CER=True,
)
test_set_wers[key] = wer

Expand Down
8 changes: 6 additions & 2 deletions egs/aishell/ASR/conformer_mmi/decode.py
Original file line number Diff line number Diff line change
Expand Up @@ -431,7 +431,7 @@ def save_results(
for key, results in results_dict.items():
recog_path = params.exp_dir / f"recogs-{test_set_name}-{key}.txt"
results = sorted(results)
store_transcripts(filename=recog_path, texts=results)
store_transcripts(filename=recog_path, texts=results, char_level=True)
if enable_log:
logging.info(f"The transcripts are stored in {recog_path}")

Expand All @@ -444,7 +444,11 @@ def save_results(
results_char.append((res[0], list("".join(res[1])), list("".join(res[2]))))
with open(errs_filename, "w") as f:
wer = write_error_stats(
f, f"{test_set_name}-{key}", results_char, enable_log=enable_log
f,
f"{test_set_name}-{key}",
results_char,
enable_log=enable_log,
cer=True,
JinZr marked this conversation as resolved.
Show resolved Hide resolved
)
test_set_wers[key] = wer

Expand Down
8 changes: 6 additions & 2 deletions egs/aishell/ASR/pruned_transducer_stateless2/decode.py
Original file line number Diff line number Diff line change
Expand Up @@ -390,7 +390,7 @@ def save_results(
for key, results in results_dict.items():
recog_path = params.res_dir / f"recogs-{test_set_name}-{params.suffix}.txt"
results = sorted(results)
store_transcripts(filename=recog_path, texts=results)
store_transcripts(filename=recog_path, texts=results, char_level=True)
logging.info(f"The transcripts are stored in {recog_path}")

# The following prints out WERs, per-word error statistics and aligned
Expand All @@ -402,7 +402,11 @@ def save_results(
results_char.append((res[0], list("".join(res[1])), list("".join(res[2]))))
with open(errs_filename, "w") as f:
wer = write_error_stats(
f, f"{test_set_name}-{key}", results_char, enable_log=True
f,
f"{test_set_name}-{key}",
results_char,
enable_log=True,
compute_CER=True,
)
test_set_wers[key] = wer

Expand Down
8 changes: 6 additions & 2 deletions egs/aishell/ASR/pruned_transducer_stateless3/decode.py
Original file line number Diff line number Diff line change
Expand Up @@ -526,7 +526,7 @@ def save_results(
for key, results in results_dict.items():
recog_path = params.res_dir / f"recogs-{test_set_name}-{params.suffix}.txt"
results = sorted(results)
store_transcripts(filename=recog_path, texts=results)
store_transcripts(filename=recog_path, texts=results, char_level=True)
logging.info(f"The transcripts are stored in {recog_path}")

# The following prints out WERs, per-word error statistics and aligned
Expand All @@ -538,7 +538,11 @@ def save_results(
results_char.append((res[0], list("".join(res[1])), list("".join(res[2]))))
with open(errs_filename, "w") as f:
wer = write_error_stats(
f, f"{test_set_name}-{key}", results_char, enable_log=True
f,
f"{test_set_name}-{key}",
results_char,
enable_log=True,
compute_CER=True,
)
test_set_wers[key] = wer

Expand Down
8 changes: 6 additions & 2 deletions egs/aishell/ASR/pruned_transducer_stateless7/decode.py
Original file line number Diff line number Diff line change
Expand Up @@ -444,15 +444,19 @@ def save_results(
for res in results:
results_char.append((res[0], list("".join(res[1])), list("".join(res[2]))))

store_transcripts(filename=recog_path, texts=results_char)
store_transcripts(filename=recog_path, texts=results_char, char_level=True)
logging.info(f"The transcripts are stored in {recog_path}")

# The following prints out WERs, per-word error statistics and aligned
# ref/hyp pairs.
errs_filename = params.res_dir / f"errs-{test_set_name}-{params.suffix}.txt"
with open(errs_filename, "w") as f:
wer = write_error_stats(
f, f"{test_set_name}-{key}", results_char, enable_log=True
f,
f"{test_set_name}-{key}",
results_char,
enable_log=True,
compute_CER=True,
)
test_set_wers[key] = wer

Expand Down
8 changes: 6 additions & 2 deletions egs/aishell/ASR/pruned_transducer_stateless7_bbpe/decode.py
Original file line number Diff line number Diff line change
Expand Up @@ -581,7 +581,7 @@ def save_results(
for key, results in results_dict.items():
recog_path = params.res_dir / f"recogs-{test_set_name}-{params.suffix}.txt"
results = sorted(results)
store_transcripts(filename=recog_path, texts=results)
store_transcripts(filename=recog_path, texts=results, char_level=True)
logging.info(f"The transcripts are stored in {recog_path}")

# The following prints out WERs, per-word error statistics and aligned
Expand All @@ -594,7 +594,11 @@ def save_results(

with open(errs_filename, "w") as f:
wer = write_error_stats(
f, f"{test_set_name}-{key}", results_char, enable_log=True
f,
f"{test_set_name}-{key}",
results_char,
enable_log=True,
compute_CER=True,
)
test_set_wers[key] = wer

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -492,15 +492,19 @@ def save_results(
for key, results in results_dict.items():
recog_path = params.res_dir / f"recogs-{test_set_name}-{params.suffix}.txt"
results = sorted(results)
store_transcripts(filename=recog_path, texts=results)
store_transcripts(filename=recog_path, texts=results, char_level=True)
logging.info(f"The transcripts are stored in {recog_path}")

# The following prints out WERs, per-word error statistics and aligned
# ref/hyp pairs.
errs_filename = params.res_dir / f"errs-{test_set_name}-{params.suffix}.txt"
with open(errs_filename, "w") as f:
wer = write_error_stats(
f, f"{test_set_name}-{key}", results, enable_log=True
f,
f"{test_set_name}-{key}",
results,
enable_log=True,
compute_CER=True,
)
test_set_wers[key] = wer

Expand Down
10 changes: 8 additions & 2 deletions egs/aishell/ASR/tdnn_lstm_ctc/decode.py
Original file line number Diff line number Diff line change
Expand Up @@ -278,7 +278,7 @@ def save_results(
for key, results in results_dict.items():
recog_path = params.exp_dir / f"recogs-{test_set_name}-{key}.txt"
results = sorted(results)
store_transcripts(filename=recog_path, texts=results)
store_transcripts(filename=recog_path, texts=results, char_level=True)
logging.info(f"The transcripts are stored in {recog_path}")

# The following prints out WERs, per-word error statistics and aligned
Expand All @@ -289,7 +289,13 @@ def save_results(
for res in results:
results_char.append((res[0], list("".join(res[1])), list("".join(res[2]))))
with open(errs_filename, "w") as f:
wer = write_error_stats(f, f"{test_set_name}-{key}", results_char)
wer = write_error_stats(
f,
f"{test_set_name}-{key}",
results_char,
enable_log=True,
compute_CER=True,
)
test_set_wers[key] = wer

logging.info("Wrote detailed error stats to {}".format(errs_filename))
Expand Down
8 changes: 6 additions & 2 deletions egs/aishell/ASR/transducer_stateless/decode.py
Original file line number Diff line number Diff line change
Expand Up @@ -327,7 +327,7 @@ def save_results(
for key, results in results_dict.items():
recog_path = params.res_dir / f"recogs-{test_set_name}-{params.suffix}.txt"
results = sorted(results)
store_transcripts(filename=recog_path, texts=results)
store_transcripts(filename=recog_path, texts=results, char_level=True)

# The following prints out WERs, per-word error statistics and aligned
# ref/hyp pairs.
Expand All @@ -338,7 +338,11 @@ def save_results(
results_char.append((res[0], list("".join(res[1])), list("".join(res[2]))))
with open(errs_filename, "w") as f:
wer = write_error_stats(
f, f"{test_set_name}-{key}", results_char, enable_log=True
f,
f"{test_set_name}-{key}",
results_char,
enable_log=True,
compute_CER=True,
)
test_set_wers[key] = wer

Expand Down
8 changes: 6 additions & 2 deletions egs/aishell/ASR/transducer_stateless_modified-2/decode.py
Original file line number Diff line number Diff line change
Expand Up @@ -372,7 +372,7 @@ def save_results(
for key, results in results_dict.items():
recog_path = params.res_dir / f"recogs-{test_set_name}-{params.suffix}.txt"
results = sorted(results)
store_transcripts(filename=recog_path, texts=results)
store_transcripts(filename=recog_path, texts=results, char_level=True)
logging.info(f"The transcripts are stored in {recog_path}")

# The following prints out WERs, per-word error statistics and aligned
Expand All @@ -384,7 +384,11 @@ def save_results(
results_char.append((res[0], list("".join(res[1])), list("".join(res[2]))))
with open(errs_filename, "w") as f:
wer = write_error_stats(
f, f"{test_set_name}-{key}", results_char, enable_log=True
f,
f"{test_set_name}-{key}",
results_char,
enable_log=True,
compute_CER=True,
)
test_set_wers[key] = wer

Expand Down
8 changes: 6 additions & 2 deletions egs/aishell/ASR/transducer_stateless_modified/decode.py
Original file line number Diff line number Diff line change
Expand Up @@ -376,7 +376,7 @@ def save_results(
for key, results in results_dict.items():
recog_path = params.res_dir / f"recogs-{test_set_name}-{params.suffix}.txt"
results = sorted(results)
store_transcripts(filename=recog_path, texts=results)
store_transcripts(filename=recog_path, texts=results, char_level=True)
logging.info(f"The transcripts are stored in {recog_path}")

# The following prints out WERs, per-word error statistics and aligned
Expand All @@ -388,7 +388,11 @@ def save_results(
results_char.append((res[0], list("".join(res[1])), list("".join(res[2]))))
with open(errs_filename, "w") as f:
wer = write_error_stats(
f, f"{test_set_name}-{key}", results_char, enable_log=True
f,
f"{test_set_name}-{key}",
results_char,
enable_log=True,
compute_CER=True,
)
test_set_wers[key] = wer

Expand Down
8 changes: 6 additions & 2 deletions egs/aishell/ASR/whisper/decode.py
Original file line number Diff line number Diff line change
Expand Up @@ -358,7 +358,7 @@ def save_results(
params.exp_dir / f"recogs-{test_set_name}-{key}-{params.suffix}.txt"
)
results = sorted(results)
store_transcripts(filename=recog_path, texts=results)
store_transcripts(filename=recog_path, texts=results, char_level=True)
if enable_log:
logging.info(f"The transcripts are stored in {recog_path}")

Expand All @@ -373,7 +373,11 @@ def save_results(
results_char.append((res[0], list("".join(res[1])), list("".join(res[2]))))
with open(errs_filename, "w") as f:
wer = write_error_stats(
f, f"{test_set_name}-{key}", results_char, enable_log=enable_log
f,
f"{test_set_name}-{key}",
results_char,
enable_log=enable_log,
compute_CER=True,
)
test_set_wers[key] = wer

Expand Down
8 changes: 6 additions & 2 deletions egs/aishell/ASR/zipformer/decode.py
Original file line number Diff line number Diff line change
Expand Up @@ -560,7 +560,7 @@ def save_results(
params.res_dir / f"recogs-{test_set_name}-{key}-{params.suffix}.txt"
)
results = sorted(results)
store_transcripts(filename=recog_path, texts=results)
store_transcripts(filename=recog_path, texts=results, char_level=True)
logging.info(f"The transcripts are stored in {recog_path}")

# The following prints out WERs, per-word error statistics and aligned
Expand All @@ -570,7 +570,11 @@ def save_results(
)
with open(errs_filename, "w") as f:
wer = write_error_stats(
f, f"{test_set_name}-{key}", results, enable_log=True
f,
f"{test_set_name}-{key}",
results,
enable_log=True,
compute_CER=True,
)
test_set_wers[key] = wer

Expand Down
Loading