From 062eb8ff5ae4fde12d9551c2d6f1b64bf39571bd Mon Sep 17 00:00:00 2001
From: yhliang <429259365@qq.com>
Date: 星期四, 11 五月 2023 15:54:02 +0800
Subject: [PATCH] update saasr egs and m2met docs
---
docs/m2met2/_build/html/_images/qrcode.png | 0
docs/m2met2_cn/基线.md | 3
egs/alimeeting/sa-asr/asr_local.sh | 143 ++++++-----------------------------
docs/m2met2_cn/images/baseline_result.png | 0
egs/alimeeting/sa-asr/README.md | 6 +
egs/alimeeting/sa-asr/run.sh | 8 +
docs/m2met2/Baseline.md | 2
docs/m2met2_cn/images/qrcode.png | 0
docs/m2met2/_build/doctrees/Baseline.doctree | 0
docs/m2met2_cn/_build/html/_images/baseline_result.png | 0
docs/m2met2/_build/html/searchindex.js | 2
docs/m2met2_cn/_build/doctrees/environment.pickle | 0
docs/m2met2_cn/_build/doctrees/基线.doctree | 0
docs/m2met2/_build/html/Introduction.html | 12 +-
docs/m2met2/_build/html/_sources/Introduction.md.txt | 12 +-
docs/m2met2/_build/doctrees/environment.pickle | 0
docs/m2met2/_build/html/_images/baseline_result.png | 0
docs/m2met2/_build/html/_sources/Baseline.md.txt | 2
docs/m2met2/images/qrcode.png | 0
docs/m2met2_cn/_build/html/_images/qrcode.png | 0
docs/m2met2/images/baseline_result.png | 0
docs/m2met2/_build/html/Baseline.html | 2
docs/m2met2/Introduction.md | 12 +-
egs/alimeeting/sa-asr/local/download_pretrained_model_from_modelscope.py | 7 +
docs/m2met2_cn/_build/html/基线.html | 4
docs/m2met2_cn/_build/html/_sources/基线.md.txt | 3
docs/m2met2/_build/doctrees/Introduction.doctree | 0
27 files changed, 70 insertions(+), 148 deletions(-)
diff --git a/docs/m2met2/Baseline.md b/docs/m2met2/Baseline.md
index cdaff8a..4e12162 100644
--- a/docs/m2met2/Baseline.md
+++ b/docs/m2met2/Baseline.md
@@ -31,4 +31,4 @@
## Baseline results
The results of the baseline system are shown in Table 3. The speaker profile adopts the oracle speaker embedding during training. However, due to the lack of oracle speaker label during evaluation, the speaker profile provided by an additional spectral clustering is used. Meanwhile, the results of using the oracle speaker profile on Eval and Test Set are also provided to show the impact of speaker profile accuracy.
-
\ No newline at end of file
+
\ No newline at end of file
diff --git a/docs/m2met2/Introduction.md b/docs/m2met2/Introduction.md
index 06c27b2..fc7c356 100644
--- a/docs/m2met2/Introduction.md
+++ b/docs/m2met2/Introduction.md
@@ -10,14 +10,14 @@
## Timeline(AOE Time)
- $ April~29, 2023: $ Challenge and registration open.
-- $ May~8, 2023: $ Baseline release.
-- $ May~15, 2023: $ Registration deadline, the due date for participants to join the Challenge.
-- $ June~9, 2023: $ Test data release and leaderboard open.
-- $ June~13, 2023: $ Final submission deadline and leaderboar close.
-- $ June~19, 2023: $ Evaluation result and ranking release.
+- $ May~11, 2023: $ Baseline release.
+- $ May~22, 2023: $ Registration deadline, the due date for participants to join the Challenge.
+- $ June~16, 2023: $ Test data release and leaderboard open.
+- $ June~20, 2023: $ Final submission deadline and leaderboar close.
+- $ June~26, 2023: $ Evaluation result and ranking release.
- $ July~3, 2023: $ Deadline for paper submission.
- $ July~10, 2023: $ Deadline for final paper submission.
-- $ December~12\ to\ 16, 2023: $ ASRU Workshop and challenge Session
+- $ December~12\ to\ 16, 2023: $ ASRU Workshop and Challenge Session.
## Guidelines
diff --git a/docs/m2met2/_build/doctrees/Baseline.doctree b/docs/m2met2/_build/doctrees/Baseline.doctree
index a99a9af..f6ea62f 100644
--- a/docs/m2met2/_build/doctrees/Baseline.doctree
+++ b/docs/m2met2/_build/doctrees/Baseline.doctree
Binary files differ
diff --git a/docs/m2met2/_build/doctrees/Introduction.doctree b/docs/m2met2/_build/doctrees/Introduction.doctree
index 96e4276..6ffceef 100644
--- a/docs/m2met2/_build/doctrees/Introduction.doctree
+++ b/docs/m2met2/_build/doctrees/Introduction.doctree
Binary files differ
diff --git a/docs/m2met2/_build/doctrees/environment.pickle b/docs/m2met2/_build/doctrees/environment.pickle
index aae3d36..fe68059 100644
--- a/docs/m2met2/_build/doctrees/environment.pickle
+++ b/docs/m2met2/_build/doctrees/environment.pickle
Binary files differ
diff --git a/docs/m2met2/_build/html/Baseline.html b/docs/m2met2/_build/html/Baseline.html
index 7fef329..62c656c 100644
--- a/docs/m2met2/_build/html/Baseline.html
+++ b/docs/m2met2/_build/html/Baseline.html
@@ -157,7 +157,7 @@
<section id="baseline-results">
<h2>Baseline results<a class="headerlink" href="#baseline-results" title="Permalink to this heading">露</a></h2>
<p>The results of the baseline system are shown in Table 3. The speaker profile adopts the oracle speaker embedding during training. However, due to the lack of oracle speaker label during evaluation, the speaker profile provided by an additional spectral clustering is used. Meanwhile, the results of using the oracle speaker profile on Eval and Test Set are also provided to show the impact of speaker profile accuracy.</p>
-<p><img alt="baseline result" src="_images/baseline_result.png" /></p>
+<p><img alt="baseline_result" src="_images/baseline_result.png" /></p>
</section>
</section>
diff --git a/docs/m2met2/_build/html/Introduction.html b/docs/m2met2/_build/html/Introduction.html
index b3079bd..82394fc 100644
--- a/docs/m2met2/_build/html/Introduction.html
+++ b/docs/m2met2/_build/html/Introduction.html
@@ -136,14 +136,14 @@
<h2>Timeline(AOE Time)<a class="headerlink" href="#timeline-aoe-time" title="Permalink to this heading">露</a></h2>
<ul class="simple">
<li><p><span class="math notranslate nohighlight">\( April~29, 2023: \)</span> Challenge and registration open.</p></li>
-<li><p><span class="math notranslate nohighlight">\( May~8, 2023: \)</span> Baseline release.</p></li>
-<li><p><span class="math notranslate nohighlight">\( May~15, 2023: \)</span> Registration deadline, the due date for participants to join the Challenge.</p></li>
-<li><p><span class="math notranslate nohighlight">\( June~9, 2023: \)</span> Test data release and leaderboard open.</p></li>
-<li><p><span class="math notranslate nohighlight">\( June~13, 2023: \)</span> Final submission deadline and leaderboar close.</p></li>
-<li><p><span class="math notranslate nohighlight">\( June~19, 2023: \)</span> Evaluation result and ranking release.</p></li>
+<li><p><span class="math notranslate nohighlight">\( May~11, 2023: \)</span> Baseline release.</p></li>
+<li><p><span class="math notranslate nohighlight">\( May~22, 2023: \)</span> Registration deadline, the due date for participants to join the Challenge.</p></li>
+<li><p><span class="math notranslate nohighlight">\( June~16, 2023: \)</span> Test data release and leaderboard open.</p></li>
+<li><p><span class="math notranslate nohighlight">\( June~20, 2023: \)</span> Final submission deadline and leaderboar close.</p></li>
+<li><p><span class="math notranslate nohighlight">\( June~26, 2023: \)</span> Evaluation result and ranking release.</p></li>
<li><p><span class="math notranslate nohighlight">\( July~3, 2023: \)</span> Deadline for paper submission.</p></li>
<li><p><span class="math notranslate nohighlight">\( July~10, 2023: \)</span> Deadline for final paper submission.</p></li>
-<li><p><span class="math notranslate nohighlight">\( December~12\ to\ 16, 2023: \)</span> ASRU Workshop and challenge Session</p></li>
+<li><p><span class="math notranslate nohighlight">\( December~12\ to\ 16, 2023: \)</span> ASRU Workshop and Challenge Session.</p></li>
</ul>
</section>
<section id="guidelines">
diff --git a/docs/m2met2/_build/html/_images/baseline_result.png b/docs/m2met2/_build/html/_images/baseline_result.png
index d51d775..6b76361 100644
--- a/docs/m2met2/_build/html/_images/baseline_result.png
+++ b/docs/m2met2/_build/html/_images/baseline_result.png
Binary files differ
diff --git a/docs/m2met2/_build/html/_images/qrcode.png b/docs/m2met2/_build/html/_images/qrcode.png
index 54b2f55..fc4c349 100644
--- a/docs/m2met2/_build/html/_images/qrcode.png
+++ b/docs/m2met2/_build/html/_images/qrcode.png
Binary files differ
diff --git a/docs/m2met2/_build/html/_sources/Baseline.md.txt b/docs/m2met2/_build/html/_sources/Baseline.md.txt
index cdaff8a..4e12162 100644
--- a/docs/m2met2/_build/html/_sources/Baseline.md.txt
+++ b/docs/m2met2/_build/html/_sources/Baseline.md.txt
@@ -31,4 +31,4 @@
## Baseline results
The results of the baseline system are shown in Table 3. The speaker profile adopts the oracle speaker embedding during training. However, due to the lack of oracle speaker label during evaluation, the speaker profile provided by an additional spectral clustering is used. Meanwhile, the results of using the oracle speaker profile on Eval and Test Set are also provided to show the impact of speaker profile accuracy.
-
\ No newline at end of file
+
\ No newline at end of file
diff --git a/docs/m2met2/_build/html/_sources/Introduction.md.txt b/docs/m2met2/_build/html/_sources/Introduction.md.txt
index 06c27b2..fc7c356 100644
--- a/docs/m2met2/_build/html/_sources/Introduction.md.txt
+++ b/docs/m2met2/_build/html/_sources/Introduction.md.txt
@@ -10,14 +10,14 @@
## Timeline(AOE Time)
- $ April~29, 2023: $ Challenge and registration open.
-- $ May~8, 2023: $ Baseline release.
-- $ May~15, 2023: $ Registration deadline, the due date for participants to join the Challenge.
-- $ June~9, 2023: $ Test data release and leaderboard open.
-- $ June~13, 2023: $ Final submission deadline and leaderboar close.
-- $ June~19, 2023: $ Evaluation result and ranking release.
+- $ May~11, 2023: $ Baseline release.
+- $ May~22, 2023: $ Registration deadline, the due date for participants to join the Challenge.
+- $ June~16, 2023: $ Test data release and leaderboard open.
+- $ June~20, 2023: $ Final submission deadline and leaderboar close.
+- $ June~26, 2023: $ Evaluation result and ranking release.
- $ July~3, 2023: $ Deadline for paper submission.
- $ July~10, 2023: $ Deadline for final paper submission.
-- $ December~12\ to\ 16, 2023: $ ASRU Workshop and challenge Session
+- $ December~12\ to\ 16, 2023: $ ASRU Workshop and Challenge Session.
## Guidelines
diff --git a/docs/m2met2/_build/html/searchindex.js b/docs/m2met2/_build/html/searchindex.js
index 6481ef2..3387db5 100644
--- a/docs/m2met2/_build/html/searchindex.js
+++ b/docs/m2met2/_build/html/searchindex.js
@@ -1 +1 @@
-Search.setIndex({"docnames": ["Baseline", "Contact", "Dataset", "Introduction", "Organizers", "Rules", "Track_setting_and_evaluation", "index"], "filenames": ["Baseline.md", "Contact.md", "Dataset.md", "Introduction.md", "Organizers.md", "Rules.md", "Track_setting_and_evaluation.md", "index.rst"], "titles": ["Baseline", "Contact", "Datasets", "Introduction", "Organizers", "Rules", "Track & Evaluation", "ASRU 2023 MULTI-CHANNEL MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0 (M2MeT2.0)"], "terms": {"we": [0, 2, 3, 7], "releas": [0, 2, 3, 6], "an": [0, 2, 3, 6], "e2": 0, "sa": 0, "asr": [0, 3, 7], "conduct": [0, 2], "funasr": 0, "time": [0, 6], "accord": [0, 3], "timelin": [0, 2], "The": [0, 2, 3, 5, 6], "model": [0, 2, 3, 5, 6], "architectur": 0, "i": [0, 2, 3, 5], "shown": [0, 2], "figur": [0, 6], "3": [0, 2, 3], "speakerencod": 0, "initi": 0, "pre": [0, 6], "train": [0, 3, 5, 7], "speaker": [0, 2, 3, 7], "verif": 0, "from": [0, 2, 3, 5, 6], "modelscop": [0, 6], "thi": [0, 3, 5, 6], "also": [0, 2, 3, 6], "us": [0, 2, 5, 6], "extract": 0, "embed": 0, "profil": 0, "To": [0, 2, 3, 7], "run": 0, "first": 0, "you": [0, 1], "need": 0, "instal": 0, "There": [0, 2], "ar": [0, 2, 3, 5, 6, 7], "two": [0, 3, 5, 7], "startup": 0, "script": [0, 2], "sh": 0, "evalu": [0, 2, 3, 7], "old": 0, "eval": [0, 2, 5, 6], "test": [0, 2, 3, 5, 6], "set": [0, 2, 3, 5, 6], "run_m2met_2023_inf": 0, "infer": 0, "new": [0, 2, 3, 6], "multi": [0, 3, 6], "channel": [0, 3], "parti": [0, 3, 6], "meet": [0, 2, 3, 6], "transcript": [0, 2, 3, 5, 6], "2": [0, 2, 6], "0": [0, 1, 2, 3], "m2met2": [0, 1, 3], "challeng": [0, 1, 3, 5, 6], "befor": 0, "must": [0, 3, 5, 6], "manual": [0, 6], "download": [0, 2], "unpack": 0, "alimeet": [0, 1, 6], "corpu": [0, 6], "place": [0, 2], "dataset": [0, 3, 5, 6, 7], "directori": 0, "eval_ali_far": 0, "eval_ali_near": 0, "test_ali_far": 0, "test_ali_near": 0, "train_ali_far": 0, "train_ali_near": 0, "test_2023_ali_far": 0, "after": 0, "which": [0, 2, 3, 6], "contain": [0, 2, 6], "onli": [0, 2, 5, 6], "raw": 0, "audio": [0, 2, 3, 6], "Then": 0, "put": 0, "given": 0, "wav": 0, "scp": 0, "wav_raw": 0, "segment": [0, 2, 6], "utt2spk": 0, "spk2utt": 0, "data": [0, 3, 5, 6], "For": [0, 2], "more": [0, 2], "detail": [0, 3, 6], "can": [0, 2, 3, 5, 6], "see": 0, "here": 0, "system": [0, 3, 5, 6, 7], "tabl": [0, 2], "adopt": 0, "oracl": [0, 6], "dure": [0, 2, 6], "howev": [0, 3, 6], "due": [0, 3], "lack": 0, "label": [0, 5, 6], "provid": [0, 2, 6, 7], "addit": [0, 6], "spectral": 0, "cluster": 0, "meanwhil": 0, "show": 0, "impact": 0, "accuraci": [0, 6], "If": [1, 5, 6], "have": [1, 3], "ani": [1, 5, 6], "question": 1, "about": [1, 3], "pleas": 1, "u": [1, 2], "email": [1, 3, 4], "m2met": [1, 3, 6, 7], "gmail": 1, "com": [1, 4], "wechat": [1, 3], "group": [1, 2, 3], "In": [2, 3, 5], "fix": [2, 3, 7], "condit": [2, 3, 7], "restrict": 2, "three": [2, 3, 6], "publicli": [2, 6], "avail": [2, 6], "corpora": 2, "name": 2, "aishel": [2, 4, 6], "4": [2, 6], "cn": [2, 4, 6], "celeb": [2, 6], "perform": [2, 3], "call": 2, "2023": [2, 3, 5, 6], "score": [2, 6], "rank": [2, 3, 6], "describ": 2, "118": 2, "75": 2, "hour": [2, 3, 6], "speech": [2, 3, 6, 7], "total": [2, 6], "divid": [2, 6], "104": 2, "10": [2, 3, 6], "specif": [2, 6], "212": 2, "8": [2, 3], "20": 2, "session": [2, 3, 6, 7], "respect": 2, "each": [2, 3, 6], "consist": [2, 6], "15": [2, 3], "30": 2, "minut": 2, "discuss": 2, "particip": [2, 5, 6], "number": [2, 3, 6], "456": 2, "25": 2, "60": 2, "balanc": 2, "gender": 2, "coverag": 2, "collect": 2, "13": [2, 3], "venu": 2, "categor": 2, "type": 2, "small": 2, "medium": 2, "larg": [2, 3], "room": [2, 3], "size": 2, "rang": 2, "m": 2, "55": 2, "differ": [2, 3, 6], "give": 2, "varieti": 2, "acoust": [2, 3, 6], "properti": 2, "layout": 2, "paramet": [2, 5], "togeth": 2, "wall": 2, "materi": 2, "cover": 2, "cement": 2, "glass": 2, "etc": 2, "other": 2, "furnish": 2, "includ": [2, 3, 5, 6], "sofa": 2, "tv": 2, "blackboard": 2, "fan": 2, "air": 2, "condition": 2, "plant": 2, "record": [2, 6], "sit": 2, "around": 2, "microphon": [2, 3], "arrai": [2, 3], "natur": 2, "convers": 2, "distanc": 2, "5": 2, "all": [2, 3, 5, 6], "nativ": 2, "chines": 2, "speak": [2, 3], "mandarin": [2, 3], "without": 2, "strong": 2, "accent": 2, "variou": [2, 3], "kind": 2, "indoor": 2, "nois": [2, 3, 5], "limit": [2, 3, 5], "click": 2, "keyboard": 2, "door": 2, "open": [2, 3, 7], "close": [2, 3], "bubbl": 2, "made": [2, 3], "both": [2, 6], "requir": [2, 3, 6], "remain": [2, 3], "same": [2, 5], "posit": 2, "overlap": [2, 3], "between": [2, 6], "exampl": 2, "fig": 2, "1": 2, "within": [2, 3], "one": [2, 5], "ensur": 2, "ratio": 2, "select": [2, 3, 5, 6], "topic": 2, "medic": 2, "treatment": 2, "educ": 2, "busi": 2, "organ": [2, 3, 5, 6, 7], "manag": 2, "industri": [2, 3], "product": 2, "daili": 2, "routin": 2, "averag": 2, "42": 2, "27": 2, "34": 2, "76": 2, "A": [2, 4], "distribut": 2, "were": 2, "ident": [2, 6], "compris": [2, 3, 7], "therebi": 2, "share": 2, "similar": 2, "configur": 2, "field": [2, 3, 6], "signal": [2, 3], "headset": 2, "": [2, 6], "own": 2, "transcrib": [2, 3, 6], "It": [2, 6], "worth": [2, 6], "note": [2, 6], "far": [2, 3], "synchron": 2, "common": 2, "prepar": 2, "textgrid": 2, "format": 2, "inform": [2, 3], "durat": 2, "id": 2, "timestamp": [2, 6], "mention": 2, "abov": 2, "openslr": 2, "via": 2, "follow": [2, 5], "link": 2, "particularli": 2, "baselin": [2, 3, 7], "conveni": 2, "automat": [3, 7], "recognit": [3, 7], "diariz": 3, "signific": 3, "stride": 3, "recent": 3, "year": 3, "result": 3, "surg": 3, "technologi": 3, "applic": 3, "across": 3, "domain": 3, "present": 3, "uniqu": [3, 6], "complex": [3, 5], "divers": 3, "style": 3, "variabl": 3, "confer": 3, "environment": 3, "reverber": [3, 5], "over": 3, "sever": 3, "been": 3, "advanc": [3, 7], "develop": [3, 6], "rich": 3, "comput": [3, 5], "hear": 3, "multisourc": 3, "environ": 3, "chime": 3, "latest": 3, "iter": 3, "ha": 3, "particular": 3, "focu": 3, "distant": 3, "gener": 3, "topologi": 3, "scenario": 3, "while": 3, "progress": 3, "english": 3, "languag": [3, 5], "barrier": 3, "achiev": 3, "compar": 3, "non": 3, "multimod": 3, "base": 3, "process": [3, 6], "misp": 3, "instrument": 3, "seek": 3, "address": 3, "problem": 3, "visual": 3, "everydai": 3, "home": 3, "focus": 3, "tackl": 3, "issu": 3, "offlin": 3, "icassp2022": 3, "main": 3, "task": [3, 6, 7], "former": 3, "involv": [3, 6], "identifi": 3, "who": 3, "spoke": 3, "when": 3, "latter": 3, "aim": 3, "multipl": [3, 6], "simultan": 3, "pose": [3, 6], "technic": 3, "difficulti": 3, "interfer": 3, "build": [3, 6, 7], "success": [3, 7], "previou": 3, "excit": 3, "propos": [3, 7], "asru": 3, "special": [3, 5, 7], "origin": [3, 5], "metric": [3, 7], "wa": [3, 6], "independ": 3, "meant": 3, "could": 3, "determin": 3, "correspond": [3, 5], "further": 3, "current": [3, 7], "talker": [3, 7], "toward": 3, "practic": 3, "attribut": [3, 7], "sub": [3, 5, 7], "track": [3, 5, 7], "what": 3, "facilit": [3, 7], "reproduc": [3, 7], "research": [3, 4, 7], "offer": 3, "comprehens": [3, 7], "overview": [3, 7], "rule": [3, 7], "furthermor": 3, "carefulli": 3, "curat": 3, "approxim": [3, 6], "design": 3, "enabl": 3, "valid": 3, "state": [3, 6, 7], "art": [3, 7], "area": 3, "april": 3, "29": 3, "registr": 3, "mai": 3, "deadlin": 3, "date": 3, "join": 3, "june": 3, "9": 3, "leaderboard": 3, "final": [3, 5, 6], "submiss": 3, "leaderboar": 3, "19": 3, "juli": 3, "paper": [3, 6], "decemb": 3, "12": 3, "16": 3, "workshop": 3, "interest": 3, "whether": 3, "academia": 3, "regist": 3, "complet": 3, "googl": 3, "form": 3, "below": 3, "22": 3, "welcom": 3, "keep": 3, "up": 3, "updat": 3, "work": 3, "dai": 3, "send": 3, "invit": 3, "elig": [3, 5], "team": 3, "qualifi": 3, "adher": [3, 5], "publish": 3, "page": 3, "prior": 3, "submit": 3, "descript": [3, 6], "document": 3, "approach": [3, 5], "method": 3, "top": 3, "asru2023": [3, 7], "proceed": 3, "lei": 4, "xie": 4, "professor": 4, "foundat": 4, "china": 4, "lxie": 4, "nwpu": 4, "edu": 4, "kong": 4, "aik": 4, "lee": 4, "senior": 4, "scientist": 4, "institut": 4, "infocomm": 4, "star": 4, "singapor": 4, "kongaik": 4, "ieee": 4, "org": 4, "zhiji": 4, "yan": 4, "princip": 4, "engin": 4, "alibaba": 4, "yzj": 4, "inc": 4, "shiliang": 4, "zhang": 4, "sly": 4, "zsl": 4, "yanmin": 4, "qian": 4, "shanghai": 4, "jiao": 4, "tong": 4, "univers": 4, "yanminqian": 4, "sjtu": 4, "zhuo": 4, "chen": 4, "appli": 4, "microsoft": 4, "usa": 4, "zhuc": 4, "jian": 4, "wu": 4, "wujian": 4, "hui": 4, "bu": 4, "ceo": 4, "buhui": 4, "aishelldata": 4, "should": 5, "augment": 5, "allow": [5, 6], "ad": 5, "speed": 5, "perturb": 5, "tone": 5, "chang": 5, "permit": 5, "purpos": 5, "instead": [5, 6], "util": [5, 6], "tune": 5, "violat": 5, "strictli": [5, 6], "prohibit": [5, 6], "fine": 5, "cpcer": [5, 6], "lower": 5, "judg": 5, "superior": 5, "forc": 5, "align": 5, "obtain": [5, 6], "frame": 5, "level": 5, "classif": 5, "basi": 5, "shallow": 5, "fusion": 5, "end": 5, "e": [5, 6], "g": 5, "la": 5, "rnnt": 5, "transform": [5, 6], "come": 5, "right": 5, "interpret": 5, "belong": 5, "case": 5, "circumst": 5, "coordin": 5, "assign": 6, "illustr": 6, "aishell4": 6, "constrain": 6, "sourc": 6, "addition": 6, "soon": 6, "simpl": 6, "voic": 6, "activ": 6, "detect": 6, "vad": 6, "concaten": 6, "minimum": 6, "permut": 6, "charact": 6, "error": 6, "rate": 6, "calcul": 6, "step": 6, "firstli": 6, "refer": 6, "hypothesi": 6, "chronolog": 6, "order": 6, "secondli": 6, "cer": 6, "repeat": 6, "possibl": 6, "lowest": 6, "tthe": 6, "insert": 6, "Ins": 6, "substitut": 6, "delet": 6, "del": 6, "output": 6, "text": 6, "frac": 6, "mathcal": 6, "n_": 6, "100": 6, "where": 6, "usag": 6, "third": 6, "hug": 6, "face": 6, "list": 6, "clearli": 6, "privat": 6, "simul": 6, "thei": 6, "mandatori": 6, "clear": 6, "scheme": 6, "delight": 7, "introduct": 7, "contact": 7}, "objects": {}, "objtypes": {}, "objnames": {}, "titleterms": {"baselin": 0, "overview": [0, 2], "quick": 0, "start": 0, "result": 0, "contact": 1, "dataset": 2, "train": [2, 6], "data": 2, "detail": 2, "alimeet": 2, "corpu": 2, "get": 2, "introduct": 3, "call": 3, "particip": 3, "timelin": 3, "aoe": 3, "time": 3, "guidelin": 3, "organ": 4, "rule": 5, "track": 6, "evalu": 6, "speaker": 6, "attribut": 6, "asr": 6, "metric": 6, "sub": 6, "arrang": 6, "i": 6, "fix": 6, "condit": 6, "ii": 6, "open": 6, "asru": 7, "2023": 7, "multi": 7, "channel": 7, "parti": 7, "meet": 7, "transcript": 7, "challeng": 7, "2": 7, "0": 7, "m2met2": 7, "content": 7}, "envversion": {"sphinx.domains.c": 2, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 8, "sphinx.domains.index": 1, "sphinx.domains.javascript": 2, "sphinx.domains.math": 2, "sphinx.domains.python": 3, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx": 57}, "alltitles": {"Baseline": [[0, "baseline"]], "Overview": [[0, "overview"]], "Quick start": [[0, "quick-start"]], "Baseline results": [[0, "baseline-results"]], "Contact": [[1, "contact"]], "Datasets": [[2, "datasets"]], "Overview of training data": [[2, "overview-of-training-data"]], "Detail of AliMeeting corpus": [[2, "detail-of-alimeeting-corpus"]], "Get the data": [[2, "get-the-data"]], "Introduction": [[3, "introduction"]], "Call for participation": [[3, "call-for-participation"]], "Timeline(AOE Time)": [[3, "timeline-aoe-time"]], "Guidelines": [[3, "guidelines"]], "Organizers": [[4, "organizers"]], "Rules": [[5, "rules"]], "Track & Evaluation": [[6, "track-evaluation"]], "Speaker-Attributed ASR": [[6, "speaker-attributed-asr"]], "Evaluation metric": [[6, "evaluation-metric"]], "Sub-track arrangement": [[6, "sub-track-arrangement"]], "Sub-track I (Fixed Training Condition):": [[6, "sub-track-i-fixed-training-condition"]], "Sub-track II (Open Training Condition):": [[6, "sub-track-ii-open-training-condition"]], "ASRU 2023 MULTI-CHANNEL MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0 (M2MeT2.0)": [[7, "asru-2023-multi-channel-multi-party-meeting-transcription-challenge-2-0-m2met2-0"]], "Contents:": [[7, null]]}, "indexentries": {}})
\ No newline at end of file
+Search.setIndex({"docnames": ["Baseline", "Contact", "Dataset", "Introduction", "Organizers", "Rules", "Track_setting_and_evaluation", "index"], "filenames": ["Baseline.md", "Contact.md", "Dataset.md", "Introduction.md", "Organizers.md", "Rules.md", "Track_setting_and_evaluation.md", "index.rst"], "titles": ["Baseline", "Contact", "Datasets", "Introduction", "Organizers", "Rules", "Track & Evaluation", "ASRU 2023 MULTI-CHANNEL MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0 (M2MeT2.0)"], "terms": {"we": [0, 2, 3, 7], "releas": [0, 2, 3, 6], "an": [0, 2, 3, 6], "e2": 0, "sa": 0, "asr": [0, 3, 7], "conduct": [0, 2], "funasr": 0, "time": [0, 6], "accord": [0, 3], "timelin": [0, 2], "The": [0, 2, 3, 5, 6], "model": [0, 2, 3, 5, 6], "architectur": 0, "i": [0, 2, 3, 5], "shown": [0, 2], "figur": [0, 6], "3": [0, 2, 3], "speakerencod": 0, "initi": 0, "pre": [0, 6], "train": [0, 3, 5, 7], "speaker": [0, 2, 3, 7], "verif": 0, "from": [0, 2, 3, 5, 6], "modelscop": [0, 6], "thi": [0, 3, 5, 6], "also": [0, 2, 3, 6], "us": [0, 2, 5, 6], "extract": 0, "embed": 0, "profil": 0, "To": [0, 2, 3, 7], "run": 0, "first": 0, "you": [0, 1], "need": 0, "instal": 0, "There": [0, 2], "ar": [0, 2, 3, 5, 6, 7], "two": [0, 3, 5, 7], "startup": 0, "script": [0, 2], "sh": 0, "evalu": [0, 2, 3, 7], "old": 0, "eval": [0, 2, 5, 6], "test": [0, 2, 3, 5, 6], "set": [0, 2, 3, 5, 6], "run_m2met_2023_inf": 0, "infer": 0, "new": [0, 2, 3, 6], "multi": [0, 3, 6], "channel": [0, 3], "parti": [0, 3, 6], "meet": [0, 2, 3, 6], "transcript": [0, 2, 3, 5, 6], "2": [0, 2, 6], "0": [0, 1, 2, 3], "m2met2": [0, 1, 3], "challeng": [0, 1, 3, 5, 6], "befor": 0, "must": [0, 3, 5, 6], "manual": [0, 6], "download": [0, 2], "unpack": 0, "alimeet": [0, 1, 6], "corpu": [0, 6], "place": [0, 2], "dataset": [0, 3, 5, 6, 7], "directori": 0, "eval_ali_far": 0, "eval_ali_near": 0, "test_ali_far": 0, "test_ali_near": 0, "train_ali_far": 0, "train_ali_near": 0, "test_2023_ali_far": 0, "after": 0, "which": [0, 2, 3, 6], "contain": [0, 2, 6], "onli": [0, 2, 5, 6], "raw": 0, "audio": [0, 2, 3, 6], "Then": 0, "put": 0, "given": 0, "wav": 0, "scp": 0, "wav_raw": 0, "segment": [0, 2, 6], "utt2spk": 0, "spk2utt": 0, "data": [0, 3, 5, 6], "For": [0, 2], "more": [0, 2], "detail": [0, 3, 6], "can": [0, 2, 3, 5, 6], "see": 0, "here": 0, "system": [0, 3, 5, 6, 7], "tabl": [0, 2], "adopt": 0, "oracl": [0, 6], "dure": [0, 2, 6], "howev": [0, 3, 6], "due": [0, 3], "lack": 0, "label": [0, 5, 6], "provid": [0, 2, 6, 7], "addit": [0, 6], "spectral": 0, "cluster": 0, "meanwhil": 0, "show": 0, "impact": 0, "accuraci": [0, 6], "If": [1, 5, 6], "have": [1, 3], "ani": [1, 5, 6], "question": 1, "about": [1, 3], "pleas": 1, "u": [1, 2], "email": [1, 3, 4], "m2met": [1, 3, 6, 7], "gmail": 1, "com": [1, 4], "wechat": [1, 3], "group": [1, 2, 3], "In": [2, 3, 5], "fix": [2, 3, 7], "condit": [2, 3, 7], "restrict": 2, "three": [2, 3, 6], "publicli": [2, 6], "avail": [2, 6], "corpora": 2, "name": 2, "aishel": [2, 4, 6], "4": [2, 6], "cn": [2, 4, 6], "celeb": [2, 6], "perform": [2, 3], "call": 2, "2023": [2, 3, 5, 6], "score": [2, 6], "rank": [2, 3, 6], "describ": 2, "118": 2, "75": 2, "hour": [2, 3, 6], "speech": [2, 3, 6, 7], "total": [2, 6], "divid": [2, 6], "104": 2, "10": [2, 3, 6], "specif": [2, 6], "212": 2, "8": 2, "20": [2, 3], "session": [2, 3, 6, 7], "respect": 2, "each": [2, 3, 6], "consist": [2, 6], "15": 2, "30": 2, "minut": 2, "discuss": 2, "particip": [2, 5, 6], "number": [2, 3, 6], "456": 2, "25": 2, "60": 2, "balanc": 2, "gender": 2, "coverag": 2, "collect": 2, "13": 2, "venu": 2, "categor": 2, "type": 2, "small": 2, "medium": 2, "larg": [2, 3], "room": [2, 3], "size": 2, "rang": 2, "m": 2, "55": 2, "differ": [2, 3, 6], "give": 2, "varieti": 2, "acoust": [2, 3, 6], "properti": 2, "layout": 2, "paramet": [2, 5], "togeth": 2, "wall": 2, "materi": 2, "cover": 2, "cement": 2, "glass": 2, "etc": 2, "other": 2, "furnish": 2, "includ": [2, 3, 5, 6], "sofa": 2, "tv": 2, "blackboard": 2, "fan": 2, "air": 2, "condition": 2, "plant": 2, "record": [2, 6], "sit": 2, "around": 2, "microphon": [2, 3], "arrai": [2, 3], "natur": 2, "convers": 2, "distanc": 2, "5": 2, "all": [2, 3, 5, 6], "nativ": 2, "chines": 2, "speak": [2, 3], "mandarin": [2, 3], "without": 2, "strong": 2, "accent": 2, "variou": [2, 3], "kind": 2, "indoor": 2, "nois": [2, 3, 5], "limit": [2, 3, 5], "click": 2, "keyboard": 2, "door": 2, "open": [2, 3, 7], "close": [2, 3], "bubbl": 2, "made": [2, 3], "both": [2, 6], "requir": [2, 3, 6], "remain": [2, 3], "same": [2, 5], "posit": 2, "overlap": [2, 3], "between": [2, 6], "exampl": 2, "fig": 2, "1": 2, "within": [2, 3], "one": [2, 5], "ensur": 2, "ratio": 2, "select": [2, 3, 5, 6], "topic": 2, "medic": 2, "treatment": 2, "educ": 2, "busi": 2, "organ": [2, 3, 5, 6, 7], "manag": 2, "industri": [2, 3], "product": 2, "daili": 2, "routin": 2, "averag": 2, "42": 2, "27": 2, "34": 2, "76": 2, "A": [2, 4], "distribut": 2, "were": 2, "ident": [2, 6], "compris": [2, 3, 7], "therebi": 2, "share": 2, "similar": 2, "configur": 2, "field": [2, 3, 6], "signal": [2, 3], "headset": 2, "": [2, 6], "own": 2, "transcrib": [2, 3, 6], "It": [2, 6], "worth": [2, 6], "note": [2, 6], "far": [2, 3], "synchron": 2, "common": 2, "prepar": 2, "textgrid": 2, "format": 2, "inform": [2, 3], "durat": 2, "id": 2, "timestamp": [2, 6], "mention": 2, "abov": 2, "openslr": 2, "via": 2, "follow": [2, 5], "link": 2, "particularli": 2, "baselin": [2, 3, 7], "conveni": 2, "automat": [3, 7], "recognit": [3, 7], "diariz": 3, "signific": 3, "stride": 3, "recent": 3, "year": 3, "result": 3, "surg": 3, "technologi": 3, "applic": 3, "across": 3, "domain": 3, "present": 3, "uniqu": [3, 6], "complex": [3, 5], "divers": 3, "style": 3, "variabl": 3, "confer": 3, "environment": 3, "reverber": [3, 5], "over": 3, "sever": 3, "been": 3, "advanc": [3, 7], "develop": [3, 6], "rich": 3, "comput": [3, 5], "hear": 3, "multisourc": 3, "environ": 3, "chime": 3, "latest": 3, "iter": 3, "ha": 3, "particular": 3, "focu": 3, "distant": 3, "gener": 3, "topologi": 3, "scenario": 3, "while": 3, "progress": 3, "english": 3, "languag": [3, 5], "barrier": 3, "achiev": 3, "compar": 3, "non": 3, "multimod": 3, "base": 3, "process": [3, 6], "misp": 3, "instrument": 3, "seek": 3, "address": 3, "problem": 3, "visual": 3, "everydai": 3, "home": 3, "focus": 3, "tackl": 3, "issu": 3, "offlin": 3, "icassp2022": 3, "main": 3, "task": [3, 6, 7], "former": 3, "involv": [3, 6], "identifi": 3, "who": 3, "spoke": 3, "when": 3, "latter": 3, "aim": 3, "multipl": [3, 6], "simultan": 3, "pose": [3, 6], "technic": 3, "difficulti": 3, "interfer": 3, "build": [3, 6, 7], "success": [3, 7], "previou": 3, "excit": 3, "propos": [3, 7], "asru": 3, "special": [3, 5, 7], "origin": [3, 5], "metric": [3, 7], "wa": [3, 6], "independ": 3, "meant": 3, "could": 3, "determin": 3, "correspond": [3, 5], "further": 3, "current": [3, 7], "talker": [3, 7], "toward": 3, "practic": 3, "attribut": [3, 7], "sub": [3, 5, 7], "track": [3, 5, 7], "what": 3, "facilit": [3, 7], "reproduc": [3, 7], "research": [3, 4, 7], "offer": 3, "comprehens": [3, 7], "overview": [3, 7], "rule": [3, 7], "furthermor": 3, "carefulli": 3, "curat": 3, "approxim": [3, 6], "design": 3, "enabl": 3, "valid": 3, "state": [3, 6, 7], "art": [3, 7], "area": 3, "april": 3, "29": 3, "registr": 3, "mai": 3, "11": 3, "22": 3, "deadlin": 3, "date": 3, "join": 3, "june": 3, "16": 3, "leaderboard": 3, "final": [3, 5, 6], "submiss": 3, "leaderboar": 3, "26": 3, "juli": 3, "paper": [3, 6], "decemb": 3, "12": 3, "workshop": 3, "interest": 3, "whether": 3, "academia": 3, "regist": 3, "complet": 3, "googl": 3, "form": 3, "below": 3, "welcom": 3, "keep": 3, "up": 3, "updat": 3, "work": 3, "dai": 3, "send": 3, "invit": 3, "elig": [3, 5], "team": 3, "qualifi": 3, "adher": [3, 5], "publish": 3, "page": 3, "prior": 3, "submit": 3, "descript": [3, 6], "document": 3, "approach": [3, 5], "method": 3, "top": 3, "asru2023": [3, 7], "proceed": 3, "lei": 4, "xie": 4, "professor": 4, "foundat": 4, "china": 4, "lxie": 4, "nwpu": 4, "edu": 4, "kong": 4, "aik": 4, "lee": 4, "senior": 4, "scientist": 4, "institut": 4, "infocomm": 4, "star": 4, "singapor": 4, "kongaik": 4, "ieee": 4, "org": 4, "zhiji": 4, "yan": 4, "princip": 4, "engin": 4, "alibaba": 4, "yzj": 4, "inc": 4, "shiliang": 4, "zhang": 4, "sly": 4, "zsl": 4, "yanmin": 4, "qian": 4, "shanghai": 4, "jiao": 4, "tong": 4, "univers": 4, "yanminqian": 4, "sjtu": 4, "zhuo": 4, "chen": 4, "appli": 4, "microsoft": 4, "usa": 4, "zhuc": 4, "jian": 4, "wu": 4, "wujian": 4, "hui": 4, "bu": 4, "ceo": 4, "buhui": 4, "aishelldata": 4, "should": 5, "augment": 5, "allow": [5, 6], "ad": 5, "speed": 5, "perturb": 5, "tone": 5, "chang": 5, "permit": 5, "purpos": 5, "instead": [5, 6], "util": [5, 6], "tune": 5, "violat": 5, "strictli": [5, 6], "prohibit": [5, 6], "fine": 5, "cpcer": [5, 6], "lower": 5, "judg": 5, "superior": 5, "forc": 5, "align": 5, "obtain": [5, 6], "frame": 5, "level": 5, "classif": 5, "basi": 5, "shallow": 5, "fusion": 5, "end": 5, "e": [5, 6], "g": 5, "la": 5, "rnnt": 5, "transform": [5, 6], "come": 5, "right": 5, "interpret": 5, "belong": 5, "case": 5, "circumst": 5, "coordin": 5, "assign": 6, "illustr": 6, "aishell4": 6, "constrain": 6, "sourc": 6, "addition": 6, "soon": 6, "simpl": 6, "voic": 6, "activ": 6, "detect": 6, "vad": 6, "concaten": 6, "minimum": 6, "permut": 6, "charact": 6, "error": 6, "rate": 6, "calcul": 6, "step": 6, "firstli": 6, "refer": 6, "hypothesi": 6, "chronolog": 6, "order": 6, "secondli": 6, "cer": 6, "repeat": 6, "possibl": 6, "lowest": 6, "tthe": 6, "insert": 6, "Ins": 6, "substitut": 6, "delet": 6, "del": 6, "output": 6, "text": 6, "frac": 6, "mathcal": 6, "n_": 6, "100": 6, "where": 6, "usag": 6, "third": 6, "hug": 6, "face": 6, "list": 6, "clearli": 6, "privat": 6, "simul": 6, "thei": 6, "mandatori": 6, "clear": 6, "scheme": 6, "delight": 7, "introduct": 7, "contact": 7}, "objects": {}, "objtypes": {}, "objnames": {}, "titleterms": {"baselin": 0, "overview": [0, 2], "quick": 0, "start": 0, "result": 0, "contact": 1, "dataset": 2, "train": [2, 6], "data": 2, "detail": 2, "alimeet": 2, "corpu": 2, "get": 2, "introduct": 3, "call": 3, "particip": 3, "timelin": 3, "aoe": 3, "time": 3, "guidelin": 3, "organ": 4, "rule": 5, "track": 6, "evalu": 6, "speaker": 6, "attribut": 6, "asr": 6, "metric": 6, "sub": 6, "arrang": 6, "i": 6, "fix": 6, "condit": 6, "ii": 6, "open": 6, "asru": 7, "2023": 7, "multi": 7, "channel": 7, "parti": 7, "meet": 7, "transcript": 7, "challeng": 7, "2": 7, "0": 7, "m2met2": 7, "content": 7}, "envversion": {"sphinx.domains.c": 2, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 8, "sphinx.domains.index": 1, "sphinx.domains.javascript": 2, "sphinx.domains.math": 2, "sphinx.domains.python": 3, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx": 57}, "alltitles": {"Baseline": [[0, "baseline"]], "Overview": [[0, "overview"]], "Quick start": [[0, "quick-start"]], "Baseline results": [[0, "baseline-results"]], "Contact": [[1, "contact"]], "Datasets": [[2, "datasets"]], "Overview of training data": [[2, "overview-of-training-data"]], "Detail of AliMeeting corpus": [[2, "detail-of-alimeeting-corpus"]], "Get the data": [[2, "get-the-data"]], "Introduction": [[3, "introduction"]], "Call for participation": [[3, "call-for-participation"]], "Timeline(AOE Time)": [[3, "timeline-aoe-time"]], "Guidelines": [[3, "guidelines"]], "Organizers": [[4, "organizers"]], "Rules": [[5, "rules"]], "Track & Evaluation": [[6, "track-evaluation"]], "Speaker-Attributed ASR": [[6, "speaker-attributed-asr"]], "Evaluation metric": [[6, "evaluation-metric"]], "Sub-track arrangement": [[6, "sub-track-arrangement"]], "Sub-track I (Fixed Training Condition):": [[6, "sub-track-i-fixed-training-condition"]], "Sub-track II (Open Training Condition):": [[6, "sub-track-ii-open-training-condition"]], "ASRU 2023 MULTI-CHANNEL MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0 (M2MeT2.0)": [[7, "asru-2023-multi-channel-multi-party-meeting-transcription-challenge-2-0-m2met2-0"]], "Contents:": [[7, null]]}, "indexentries": {}})
\ No newline at end of file
diff --git a/docs/m2met2/images/baseline_result.png b/docs/m2met2/images/baseline_result.png
index d51d775..6b76361 100644
--- a/docs/m2met2/images/baseline_result.png
+++ b/docs/m2met2/images/baseline_result.png
Binary files differ
diff --git a/docs/m2met2/images/qrcode.png b/docs/m2met2/images/qrcode.png
index 54b2f55..fc4c349 100644
--- a/docs/m2met2/images/qrcode.png
+++ b/docs/m2met2/images/qrcode.png
Binary files differ
diff --git a/docs/m2met2_cn/_build/doctrees/environment.pickle b/docs/m2met2_cn/_build/doctrees/environment.pickle
index 178fe18..8426df6 100644
--- a/docs/m2met2_cn/_build/doctrees/environment.pickle
+++ b/docs/m2met2_cn/_build/doctrees/environment.pickle
Binary files differ
diff --git "a/docs/m2met2_cn/_build/doctrees/\345\237\272\347\272\277.doctree" "b/docs/m2met2_cn/_build/doctrees/\345\237\272\347\272\277.doctree"
index 9215986..e9e895c 100644
--- "a/docs/m2met2_cn/_build/doctrees/\345\237\272\347\272\277.doctree"
+++ "b/docs/m2met2_cn/_build/doctrees/\345\237\272\347\272\277.doctree"
Binary files differ
diff --git a/docs/m2met2_cn/_build/html/_images/baseline_result.png b/docs/m2met2_cn/_build/html/_images/baseline_result.png
index d51d775..6b76361 100644
--- a/docs/m2met2_cn/_build/html/_images/baseline_result.png
+++ b/docs/m2met2_cn/_build/html/_images/baseline_result.png
Binary files differ
diff --git a/docs/m2met2_cn/_build/html/_images/qrcode.png b/docs/m2met2_cn/_build/html/_images/qrcode.png
index 54b2f55..fc4c349 100644
--- a/docs/m2met2_cn/_build/html/_images/qrcode.png
+++ b/docs/m2met2_cn/_build/html/_images/qrcode.png
Binary files differ
diff --git "a/docs/m2met2_cn/_build/html/_sources/\345\237\272\347\272\277.md.txt" "b/docs/m2met2_cn/_build/html/_sources/\345\237\272\347\272\277.md.txt"
index fab780b..e8fc32c 100644
--- "a/docs/m2met2_cn/_build/html/_sources/\345\237\272\347\272\277.md.txt"
+++ "b/docs/m2met2_cn/_build/html/_sources/\345\237\272\347\272\277.md.txt"
@@ -29,4 +29,5 @@
鏇村鍩虹嚎绯荤粺璇︽儏瑙乕姝ゅ](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs/alimeeting/sa-asr/README.md)
## 鍩虹嚎缁撴灉
鍩虹嚎绯荤粺鐨勭粨鏋滃琛�3鎵�绀恒�傚湪璁粌鏈熼棿锛岃璇濅汉妗ｆ閲囩敤浜嗙湡瀹炶璇濅汉宓屽叆銆傜劧鑰岀敱浜庡湪璇勪及杩囩▼涓己涔忕湡瀹炶璇濅汉鏍囩锛屽洜姝や娇鐢ㄤ簡鐢遍澶栫殑璋辫仛绫绘彁渚涚殑璇磋瘽浜虹壒寰併�傚悓鏃舵垜浠繕鎻愪緵浜嗗湪璇勪及鍜屾祴璇曢泦涓婁娇鐢ㄧ湡瀹炶璇濅汉妗ｆ鐨勭粨鏋滐紝浠ユ樉绀鸿璇濅汉妗ｆ鍑嗙‘鎬х殑褰卞搷銆�
-
\ No newline at end of file
+
+
\ No newline at end of file
diff --git "a/docs/m2met2_cn/_build/html/\345\237\272\347\272\277.html" "b/docs/m2met2_cn/_build/html/\345\237\272\347\272\277.html"
index 7bfec93..f1afb2d 100644
--- "a/docs/m2met2_cn/_build/html/\345\237\272\347\272\277.html"
+++ "b/docs/m2met2_cn/_build/html/\345\237\272\347\272\277.html"
@@ -157,8 +157,8 @@
</section>
<section id="id4">
<h2>鍩虹嚎缁撴灉<a class="headerlink" href="#id4" title="姝ゆ爣棰樼殑姘镐箙閾炬帴">露</a></h2>
-<p>鍩虹嚎绯荤粺鐨勭粨鏋滃琛�3鎵�绀恒�傚湪璁粌鏈熼棿锛岃璇濅汉妗ｆ閲囩敤浜嗙湡瀹炶璇濅汉宓屽叆銆傜劧鑰岀敱浜庡湪璇勪及杩囩▼涓己涔忕湡瀹炶璇濅汉鏍囩锛屽洜姝や娇鐢ㄤ簡鐢遍澶栫殑璋辫仛绫绘彁渚涚殑璇磋瘽浜虹壒寰併�傚悓鏃舵垜浠繕鎻愪緵浜嗗湪璇勪及鍜屾祴璇曢泦涓婁娇鐢ㄧ湡瀹炶璇濅汉妗ｆ鐨勭粨鏋滐紝浠ユ樉绀鸿璇濅汉妗ｆ鍑嗙‘鎬х殑褰卞搷銆�
-<img alt="baseline result" src="_images/baseline_result.png" /></p>
+<p>鍩虹嚎绯荤粺鐨勭粨鏋滃琛�3鎵�绀恒�傚湪璁粌鏈熼棿锛岃璇濅汉妗ｆ閲囩敤浜嗙湡瀹炶璇濅汉宓屽叆銆傜劧鑰岀敱浜庡湪璇勪及杩囩▼涓己涔忕湡瀹炶璇濅汉鏍囩锛屽洜姝や娇鐢ㄤ簡鐢遍澶栫殑璋辫仛绫绘彁渚涚殑璇磋瘽浜虹壒寰併�傚悓鏃舵垜浠繕鎻愪緵浜嗗湪璇勪及鍜屾祴璇曢泦涓婁娇鐢ㄧ湡瀹炶璇濅汉妗ｆ鐨勭粨鏋滐紝浠ユ樉绀鸿璇濅汉妗ｆ鍑嗙‘鎬х殑褰卞搷銆�</p>
+<p><img alt="baseline_result" src="_images/baseline_result.png" /></p>
</section>
</section>
diff --git a/docs/m2met2_cn/images/baseline_result.png b/docs/m2met2_cn/images/baseline_result.png
index d51d775..6b76361 100644
--- a/docs/m2met2_cn/images/baseline_result.png
+++ b/docs/m2met2_cn/images/baseline_result.png
Binary files differ
diff --git a/docs/m2met2_cn/images/qrcode.png b/docs/m2met2_cn/images/qrcode.png
index 54b2f55..fc4c349 100644
--- a/docs/m2met2_cn/images/qrcode.png
+++ b/docs/m2met2_cn/images/qrcode.png
Binary files differ
diff --git "a/docs/m2met2_cn/\345\237\272\347\272\277.md" "b/docs/m2met2_cn/\345\237\272\347\272\277.md"
index fab780b..e8fc32c 100644
--- "a/docs/m2met2_cn/\345\237\272\347\272\277.md"
+++ "b/docs/m2met2_cn/\345\237\272\347\272\277.md"
@@ -29,4 +29,5 @@
鏇村鍩虹嚎绯荤粺璇︽儏瑙乕姝ゅ](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs/alimeeting/sa-asr/README.md)
## 鍩虹嚎缁撴灉
鍩虹嚎绯荤粺鐨勭粨鏋滃琛�3鎵�绀恒�傚湪璁粌鏈熼棿锛岃璇濅汉妗ｆ閲囩敤浜嗙湡瀹炶璇濅汉宓屽叆銆傜劧鑰岀敱浜庡湪璇勪及杩囩▼涓己涔忕湡瀹炶璇濅汉鏍囩锛屽洜姝や娇鐢ㄤ簡鐢遍澶栫殑璋辫仛绫绘彁渚涚殑璇磋瘽浜虹壒寰併�傚悓鏃舵垜浠繕鎻愪緵浜嗗湪璇勪及鍜屾祴璇曢泦涓婁娇鐢ㄧ湡瀹炶璇濅汉妗ｆ鐨勭粨鏋滐紝浠ユ樉绀鸿璇濅汉妗ｆ鍑嗙‘鎬х殑褰卞搷銆�
-
\ No newline at end of file
+
+
\ No newline at end of file
diff --git a/egs/alimeeting/sa-asr/README.md b/egs/alimeeting/sa-asr/README.md
index 882345c..bc6d04c 100644
--- a/egs/alimeeting/sa-asr/README.md
+++ b/egs/alimeeting/sa-asr/README.md
@@ -19,7 +19,7 @@
stage 7 - 9: Language model training (Optional).
stage 10 - 11: ASR training (SA-ASR requires loading the pre-trained ASR model).
stage 12: SA-ASR training.
-stage 13 - 18: Inference and evaluation.
+stage 13 - 16: Inference and evaluation.
```
Before running `run_m2met_2023_infer.sh`, you need to place the new test set `Test_2023_Ali_far` (to be released after the challenge starts) in the `./dataset` directory, which contains only raw audios. Then put the given `wav.scp`, `wav_raw.scp`, `segments`, `utt2spk` and `spk2utt` in the `./data/Test_2023_Ali_far` directory.
```shell
@@ -37,6 +37,10 @@
stage 3: Inference.
stage 4: Generation of SA-ASR results required for final submission.
```
+
+The baseline model is available on [ModelScope](https://www.modelscope.cn/models/damo/speech_saasr_asr-zh-cn-16k-alimeeting/summary).
+After generate stats of AliMeeting corpus(stage 10 in `run.sh`), you can set the `infer_with_pretrained_model=true` in `run.sh` to infer with our official baseline model released on ModelScope without training.
+
# Format of Final Submission
Finally, you need to submit a file called `text_spk_merge` with the following format:
```shell
diff --git a/egs/alimeeting/sa-asr/asr_local.sh b/egs/alimeeting/sa-asr/asr_local.sh
index f8cdcd3..543352e 100755
--- a/egs/alimeeting/sa-asr/asr_local.sh
+++ b/egs/alimeeting/sa-asr/asr_local.sh
@@ -107,8 +107,8 @@
# inference_asr_model=valid.acc.best.pth
# inference_asr_model=valid.loss.ave.pth
inference_sa_asr_model=valid.acc_spk.ave.pb
-download_model= # Download a model from Model Zoo and use it for decoding.
-
+infer_with_pretrained_model=false # Use pretrained model for decoding
+download_sa_asr_model= # Download the SA-ASR model from ModelScope and use it for decoding.
# [Task dependent] Set the datadir name created by local/data.sh
train_set= # Name of training set.
valid_set= # Name of validation set used for monitoring/tuning network training.
@@ -203,7 +203,8 @@
# Note that it will overwrite args in inference config.
--inference_lm # Language modle path for decoding (default="${inference_lm}").
--inference_asr_model # ASR model path for decoding (default="${inference_asr_model}").
- --download_model # Download a model from Model Zoo and use it for decoding (default="${download_model}").
+ --infer_with_pretrained_model # Use pretrained model for decoding (default="${infer_with_pretrained_model}").
+ --download_sa_asr_model= # Download the SA-ASR model from ModelScope and use it for decoding(default="${download_sa_asr_model}").
# [Task dependent] Set the datadir name created by local/data.sh
--train_set # Name of training set (required).
@@ -304,6 +305,9 @@
lm_token_type="${token_type}"
fi
+if ${infer_with_pretrained_model}; then
+ skip_train=true
+fi
# Set tag for naming of model directory
if [ -z "${asr_tag}" ]; then
@@ -1220,119 +1224,20 @@
log "Skip the training stages"
fi
+if ${infer_with_pretrained_model}; then
+ log "Use ${download_sa_asr_model} for decoding and evaluation"
+
+ sa_asr_exp="${expdir}/${download_sa_asr_model}"
+ mkdir -p "${sa_asr_exp}"
+
+ python local/download_pretrained_model_from_modelscope.py $download_sa_asr_model ${expdir}
+ inference_sa_asr_model="model.pb"
+ inference_config=${sa_asr_exp}/decoding.yaml
+fi
if ! "${skip_eval}"; then
if [ ${stage} -le 13 ] && [ ${stop_stage} -ge 13 ]; then
- log "Stage 13: Decoding multi-talker ASR: training_dir=${asr_exp}"
-
- if ${gpu_inference}; then
- _cmd="${cuda_cmd}"
- inference_nj=$[${ngpu}*${njob_infer}]
- _ngpu=1
-
- else
- _cmd="${decode_cmd}"
- inference_nj=$inference_nj
- _ngpu=0
- fi
-
- _opts=
- if [ -n "${inference_config}" ]; then
- _opts+="--config ${inference_config} "
- fi
- if "${use_lm}"; then
- if "${use_word_lm}"; then
- _opts+="--word_lm_train_config ${lm_exp}/config.yaml "
- _opts+="--word_lm_file ${lm_exp}/${inference_lm} "
- else
- _opts+="--lm_train_config ${lm_exp}/config.yaml "
- _opts+="--lm_file ${lm_exp}/${inference_lm} "
- fi
- fi
-
- # 2. Generate run.sh
- log "Generate '${asr_exp}/${inference_tag}/run.sh'. You can resume the process from stage 13 using this script"
- mkdir -p "${asr_exp}/${inference_tag}"; echo "${run_args} --stage 13 \"\$@\"; exit \$?" > "${asr_exp}/${inference_tag}/run.sh"; chmod +x "${asr_exp}/${inference_tag}/run.sh"
-
- for dset in ${test_sets}; do
- _data="${data_feats}/${dset}"
- _dir="${asr_exp}/${inference_tag}/${dset}"
- _logdir="${_dir}/logdir"
- mkdir -p "${_logdir}"
-
- _feats_type="$(<${_data}/feats_type)"
- if [ "${_feats_type}" = raw ]; then
- _scp=wav.scp
- if [[ "${audio_format}" == *ark* ]]; then
- _type=kaldi_ark
- else
- _type=sound
- fi
- else
- _scp=feats.scp
- _type=kaldi_ark
- fi
-
- # 1. Split the key file
- key_file=${_data}/${_scp}
- split_scps=""
- _nj=$(min "${inference_nj}" "$(<${key_file} wc -l)")
- echo $_nj
- for n in $(seq "${_nj}"); do
- split_scps+=" ${_logdir}/keys.${n}.scp"
- done
- # shellcheck disable=SC2086
- utils/split_scp.pl "${key_file}" ${split_scps}
-
- # 2. Submit decoding jobs
- log "Decoding started... log: '${_logdir}/asr_inference.*.log'"
-
- ${_cmd} --gpu "${_ngpu}" --max-jobs-run "${_nj}" JOB=1:"${_nj}" "${_logdir}"/asr_inference.JOB.log \
- python -m funasr.bin.asr_inference_launch \
- --batch_size 1 \
- --mc True \
- --nbest 1 \
- --ngpu "${_ngpu}" \
- --njob ${njob_infer} \
- --gpuid_list ${device} \
- --data_path_and_name_and_type "${_data}/${_scp},speech,${_type}" \
- --key_file "${_logdir}"/keys.JOB.scp \
- --asr_train_config "${asr_exp}"/config.yaml \
- --asr_model_file "${asr_exp}"/"${inference_asr_model}" \
- --output_dir "${_logdir}"/output.JOB \
- --mode asr \
- ${_opts}
-
- # 3. Concatenates the output files from each jobs
- for f in token token_int score text; do
- for i in $(seq "${_nj}"); do
- cat "${_logdir}/output.${i}/1best_recog/${f}"
- done | LC_ALL=C sort -k1 >"${_dir}/${f}"
- done
- done
- fi
-
-
- if [ ${stage} -le 14 ] && [ ${stop_stage} -ge 14 ]; then
- log "Stage 14: Scoring multi-talker ASR"
-
- for dset in ${test_sets}; do
- _data="${data_feats}/${dset}"
- _dir="${asr_exp}/${inference_tag}/${dset}"
-
- python utils/proce_text.py ${_data}/text ${_data}/text.proc
- python utils/proce_text.py ${_dir}/text ${_dir}/text.proc
-
- python utils/compute_wer.py ${_data}/text.proc ${_dir}/text.proc ${_dir}/text.cer
- tail -n 3 ${_dir}/text.cer > ${_dir}/text.cer.txt
- cat ${_dir}/text.cer.txt
-
- done
-
- fi
-
- if [ ${stage} -le 15 ] && [ ${stop_stage} -ge 15 ]; then
- log "Stage 15: Decoding SA-ASR (oracle profile): training_dir=${sa_asr_exp}"
+ log "Stage 13: Decoding SA-ASR (oracle profile): training_dir=${sa_asr_exp}"
if ${gpu_inference}; then
_cmd="${cuda_cmd}"
@@ -1423,8 +1328,8 @@
done
fi
- if [ ${stage} -le 16 ] && [ ${stop_stage} -ge 16 ]; then
- log "Stage 16: Scoring SA-ASR (oracle profile)"
+ if [ ${stage} -le 14 ] && [ ${stop_stage} -ge 14 ]; then
+ log "Stage 14: Scoring SA-ASR (oracle profile)"
for dset in ${test_sets}; do
_data="${data_feats}/${dset}"
@@ -1448,8 +1353,8 @@
fi
- if [ ${stage} -le 17 ] && [ ${stop_stage} -ge 17 ]; then
- log "Stage 17: Decoding SA-ASR (cluster profile): training_dir=${sa_asr_exp}"
+ if [ ${stage} -le 15 ] && [ ${stop_stage} -ge 15 ]; then
+ log "Stage 15: Decoding SA-ASR (cluster profile): training_dir=${sa_asr_exp}"
if ${gpu_inference}; then
_cmd="${cuda_cmd}"
@@ -1539,8 +1444,8 @@
done
fi
- if [ ${stage} -le 18 ] && [ ${stop_stage} -ge 18 ]; then
- log "Stage 18: Scoring SA-ASR (cluster profile)"
+ if [ ${stage} -le 16 ] && [ ${stop_stage} -ge 16 ]; then
+ log "Stage 16: Scoring SA-ASR (cluster profile)"
for dset in ${test_sets}; do
_data="${data_feats}/${dset}"
diff --git a/egs/alimeeting/sa-asr/local/download_pretrained_model_from_modelscope.py b/egs/alimeeting/sa-asr/local/download_pretrained_model_from_modelscope.py
new file mode 100644
index 0000000..b4b5412
--- /dev/null
+++ b/egs/alimeeting/sa-asr/local/download_pretrained_model_from_modelscope.py
@@ -0,0 +1,7 @@
+from modelscope.hub.snapshot_download import snapshot_download
+import sys
+
+if __name__ == "__main__":
+ model_tag = sys.argv[1]
+ local_model_dir = sys.argv[2]
+ model_dir = snapshot_download(model_tag, cache_dir=local_model_dir, revision='1.0.0')
\ No newline at end of file
diff --git a/egs/alimeeting/sa-asr/run.sh b/egs/alimeeting/sa-asr/run.sh
index e5297b8..2869164 100755
--- a/egs/alimeeting/sa-asr/run.sh
+++ b/egs/alimeeting/sa-asr/run.sh
@@ -8,8 +8,8 @@
ngpu=4
device="0,1,2,3"
-stage=1
-stop_stage=18
+stage=12
+stop_stage=13
train_set=Train_Ali_far
@@ -18,6 +18,8 @@
asr_config=conf/train_asr_conformer.yaml
sa_asr_config=conf/train_sa_asr_conformer.yaml
inference_config=conf/decode_asr_rnn.yaml
+infer_with_pretrained_model=true
+download_sa_asr_model="damo/speech_saasr_asr-zh-cn-16k-alimeeting"
lm_config=conf/train_lm_transformer.yaml
use_lm=false
@@ -29,6 +31,8 @@
--stop_stage ${stop_stage} \
--gpu_inference true \
--njob_infer 4 \
+ --infer_with_pretrained_model ${infer_with_pretrained_model} \
+ --download_sa_asr_model $download_sa_asr_model \
--asr_exp exp/asr_train_multispeaker_conformer_raw_zh_char_data_alimeeting \
--sa_asr_exp exp/sa_asr_train_conformer_raw_zh_char_data_alimeeting \
--asr_stats_dir exp/asr_stats_multispeaker_conformer_raw_zh_char_data_alimeeting \
--
Gitblit v1.9.1