Freeze the speech report against the commit that fixes the prose
The report is regenerated after 10a39c5 so its stamp names the code it
describes. Speed is quoted as a range in the checklist because transcribe
seconds move with machine load (3.26s then 3.12s on this box) while WER,
denominators and word counts do not move at all.
Numbers: 258.18s of audio, WER 0.242 over 533 reference words, 80 audio atoms
and 563 word timestamps read back from the store, 0 out of order and 0 before
their own segment measured on the stored words.
This commit is contained in:
ZacharyZhang-NY committed
1 parent
10a39c5125
commit
2fa91abbc5
3 files changed
+31
-22
No files matched your search
@@ -1,21 +1,21 @@
|
||||
# ASR: what the speech reader hears (commit 709104e80)
|
||||
# ASR: what the speech reader hears (commit 10a39c512)
|
||||
|
||||
- generated 2026-10-08T02:24:47+00:00
|
||||
- generated 2026-10-08T02:37:10+00:00
|
||||
- model: Systran/faster-whisper-tiny (cpu int8, 4 threads), model.bin sha256 dcb76c6586fc06cb…
|
||||
- decode: word_timestamps=True, beam_size=1, temperature=(0.0,), condition_on_previous_text=False, vad_filter=False
|
||||
- reference: Video-MME community subtitles: third-party captions, not verbatim transcripts
|
||||
- machine: {'system': 'Linux', 'release': '6.18.40.1-microsoft-standard-WSL2', 'cpus': 32, 'threads_per_query': 4, 'load_average_1_5_15': [9.65, 2.54, 0.88]}
|
||||
- machine: {'system': 'Linux', 'release': '6.18.40.1-microsoft-standard-WSL2', 'cpus': 32, 'threads_per_query': 4, 'load_average_1_5_15': [7.73, 2.66, 1.58]}
|
||||
|
||||
| video | audio s | transcribe s | ×realtime | reference words | words | WER | mean word confidence |
|
||||
| --- | --- | --- | --- | --- | --- | --- | --- |
|
||||
| 0IdYJGBmguM | 88.93 | 1.39 | 63.9 | 201 | 219 | 0.229 | 0.861 |
|
||||
| 1q-5IIyZL20 | 109.18 | 1.33 | 82.4 | 296 | 313 | 0.253 | 0.821 |
|
||||
| 1tidNDIpKSY | 60.07 | 0.54 | 112.2 | 36 | 31 | 0.222 | 0.852 |
|
||||
| 0IdYJGBmguM | 88.93 | 1.3 | 68.4 | 201 | 219 | 0.229 | 0.861 |
|
||||
| 1q-5IIyZL20 | 109.18 | 1.28 | 85.4 | 296 | 313 | 0.253 | 0.821 |
|
||||
| 1tidNDIpKSY | 60.07 | 0.54 | 111.2 | 36 | 31 | 0.222 | 0.852 |
|
||||
|
||||
Over 3 videos and 258.18 seconds of audio: word error rate **0.242** over 533 reference words (563 words heard), transcribed in 3.26 seconds.
|
||||
Over 3 videos and 258.18 seconds of audio: word error rate **0.242** over 533 reference words (563 words heard), transcribed in 3.12 seconds.
|
||||
|
||||
Repeating the pass on the same machine gave WER 0.242 then 0.242; the transcripts were byte-identical. Decoding is greedy with no retry ladder, so a rerun is the same answer, not a new draw.
|
||||
|
||||
Ingested through the product path, the store holds 80 audio atoms from 3 sources carrying 563 word timestamps (0 out of order, 0 before their own segment) out of 133 atoms in total.
|
||||
Ingested through the product path, the store holds 80 audio atoms from 3 sources carrying 563 word timestamps (0 out of order, 0 before their own segment) out of 133 atoms in total, checked on the words as stored rather than on the model's answer.
|
||||
|
||||
The captions are not a transcript, so this WER is not a bound in either direction: a caption that drops words also hides words the model dropped. The third row has only 36 reference words, where one word moves its rate by several points — read the denominators, not the decimals.
|
||||
+14
-12
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generated_utc": "2026-10-08T02:24:47+00:00",
|
||||
"commit": "709104e80915e43a1095a270a87f09cbb611d51b",
|
||||
"generated_utc": "2026-10-08T02:37:10+00:00",
|
||||
"commit": "10a39c5125ebaf73e0ff7174b3af7af4c32bcf05",
|
||||
"model": {
|
||||
"id": "Systran/faster-whisper-tiny",
|
||||
"sha256_model_bin": "dcb76c6586fc06cbdac6dd21f14cfd129cc4cdd9dce19bf4ffa62e59cbe6e6d1",
|
||||
@@ -21,9 +21,9 @@
|
||||
"cpus": 32,
|
||||
"threads_per_query": 4,
|
||||
"load_average_1_5_15": [
|
||||
9.65,
|
||||
2.54,
|
||||
0.88
|
||||
7.73,
|
||||
2.66,
|
||||
1.58
|
||||
]
|
||||
},
|
||||
"passes": {
|
||||
@@ -54,7 +54,7 @@
|
||||
"totals": {
|
||||
"videos": 3,
|
||||
"audio_seconds": 258.18,
|
||||
"transcribe_seconds": 3.26,
|
||||
"transcribe_seconds": 3.12,
|
||||
"word_error_rate": 0.242,
|
||||
"reference_words": 533,
|
||||
"hypothesis_words": 563,
|
||||
@@ -64,14 +64,16 @@
|
||||
"atoms_all": 133,
|
||||
"speech_atoms": 80,
|
||||
"word_timestamps": 563,
|
||||
"sources": 3
|
||||
"sources": 3,
|
||||
"out_of_order_in_store": 0,
|
||||
"before_their_segment_in_store": 0
|
||||
},
|
||||
"videos": [
|
||||
{
|
||||
"video": "0IdYJGBmguM",
|
||||
"seconds": 88.93,
|
||||
"transcribe_seconds": 1.39,
|
||||
"real_time_factor": 63.9,
|
||||
"transcribe_seconds": 1.3,
|
||||
"real_time_factor": 68.4,
|
||||
"segments": 38,
|
||||
"reference_words": 201,
|
||||
"hypothesis_words": 219,
|
||||
@@ -85,8 +87,8 @@
|
||||
{
|
||||
"video": "1q-5IIyZL20",
|
||||
"seconds": 109.18,
|
||||
"transcribe_seconds": 1.33,
|
||||
"real_time_factor": 82.4,
|
||||
"transcribe_seconds": 1.28,
|
||||
"real_time_factor": 85.4,
|
||||
"segments": 39,
|
||||
"reference_words": 296,
|
||||
"hypothesis_words": 313,
|
||||
@@ -101,7 +103,7 @@
|
||||
"video": "1tidNDIpKSY",
|
||||
"seconds": 60.07,
|
||||
"transcribe_seconds": 0.54,
|
||||
"real_time_factor": 112.2,
|
||||
"real_time_factor": 111.2,
|
||||
"segments": 3,
|
||||
"reference_words": 36,
|
||||
"hypothesis_words": 31,
|
||||
|
||||
Reference in new issue
Block a user