Publish isles pooled voice bundle [Seamus]

.gitattributes

@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+anchor.wav filter=lfs diff=lfs merge=lfs -text
+asset/dingding.png filter=lfs diff=lfs merge=lfs -text
+sample/sample_0.wav filter=lfs diff=lfs merge=lfs -text
+sample/sample_1.wav filter=lfs diff=lfs merge=lfs -text
+sample/sample_2.wav filter=lfs diff=lfs merge=lfs -text
+sample/sanity.wav filter=lfs diff=lfs merge=lfs -text

CosyVoice-BlankEN/config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

CosyVoice-BlankEN/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "pad_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_p": 0.8,
+  "top_k": 20,
+  "transformers_version": "4.37.0"
+}

CosyVoice-BlankEN/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:130282af0dfa9fe5840737cc49a0d339d06075f83c5a315c3372c9a0740d0b96
+size 988097824

CosyVoice-BlankEN/tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": ["<|im_start|>", "<|im_end|>"],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

README.md

@@ -0,0 +1,138 @@
+---
+license: cc-by-sa-4.0
+base_model: FunAudioLLM/CosyVoice2-0.5B
+tags:
+  - nanites
+  - tts
+  - text-to-speech
+  - cosyvoice2
+  - anonymized-voice
+  - british-isles
+  - scottish
+  - irish
+  - welsh
+  - dialect
+language:
+  - en
+pipeline_tag: text-to-speech
+---
+
+# nanites-isles-speech-{hamish,maisie,seamus,tegan,rhys}
+
+Anonymized, dialect+gender-pooled British Isles English text-to-speech
+voices — Scottish, Irish, and Welsh English as crowdsourced in the
+**OpenSLR 83** dataset (Google, 2018–19). Built on
+[CosyVoice2-0.5B](https://huggingface.co/FunAudioLLM/CosyVoice2-0.5B)
+(Apache-2.0, from FunAudioLLM), fine-tuned separately per pool.
+
+## Personas
+
+Pooled voices ship under dialect-appropriate codenames so each identity
+is a *persona*, never a single OpenSLR speaker:
+
+| Persona | Dialect/gender | Pool | WER (medium.en) | Anon max cos |
+|---|---|---|---|---|
+| **Maisie** | Scottish female | 6 speakers / 54.4 min | 26%* | 0.911 |
+| **Hamish** | Scottish male | 6 speakers / 53.4 min | 22%* | 0.782 |
+| **Seamus** | Irish male | 3 speakers / 22.7 min (thin) | 4.2% | 0.895 |
+| **Tegan** | Welsh female | 6 speakers / 60.1 min | 8.9% | 0.871 |
+| **Rhys** | Welsh male | 6 speakers / 59.8 min | 0.0% | 0.883 |
+
+\* Scots lines are deliberately written in Scots orthography (e.g.
+"dinna fash", "ged your tea"); whisper normalizes them to standard
+spelling, so WER is inflated by orthography, not speech errors. The
+Irish/Welsh lines use standard English spelling and their WERs are
+reflective.
+
+In code/config the voices keep the functional names
+`isles-speech-scottish-female` etc. (engine + dialect + gender are
+metadata); the codenames are the display/persona names.
+
+**Hugging Face repos are persona-named** (a persona gets its own repo;
+a future voice gets a new codename, not a gender suffix):
+
+- `Nanite-Labs/nanites-isles-speech-hamish` (Scottish male)
+- `Nanite-Labs/nanites-isles-speech-maisie` (Scottish female)
+- `Nanite-Labs/nanites-isles-speech-seamus` (Irish male)
+- `Nanite-Labs/nanites-isles-speech-tegan` (Welsh female)
+- `Nanite-Labs/nanites-isles-speech-rhys` (Welsh male)
+
+## Why this approach
+
+- **Engine.** Same rationale as the sister `smoky` suite: modern line is
+  **CosyVoice 2.0** (FunAudioLLM), Apache-2.0. **XTTS is retired** in
+  this project (dormant, CPML license, poor clustering/cloning control).
+- **Identity.** A *regional anon voice* must not replicate any single
+  OpenSLR speaker. CosyVoice2 SFT collapses each dialect+gender pool
+  into **one pooled speaker ID** (`<|{pool}_pool|>`), so no single
+  speaker is recoverable at synthesis time.
+- **Anonymization.** Generation feeds the pooled campplus embedding
+  (average of the pool's members) — no reference audio from any
+  individual. Max cosine of the pooled embedding to the closest member
+  is reported per voice above (0.78–0.91; smoky reference ~0.89–0.91).
+  **Seamus's pool is thin** (3 speakers — the smallest OpenSLR set; the
+  Irish female pool does not exist in OpenSLR 83, so Irish female is
+  not offered): its anonymization margin and training-data size are
+  inherently smaller than the 6-speaker pools.
+
+## Stable persona (zero-shot anchoring)
+
+SFT mode conditions identity only through the pooled embedding, and the
+base speech flow can leak timbre from the token sequence — some
+short/locked-phrase sentences **deterministically** land in a different
+timbre region (diagnosed on Hamish: one sentence regen 3× identical but
+cosine 0.58 from his anchor). Fix, adopted for all five voices:
+**zero-shot anchoring.** Each voice dir carries `anchor.wav` +
+`anchor.txt` (a pooled-blend clip chosen by the listener, so the anchor
+is itself anonymized); `cosyvoice_infer` clones that clip's timbre for
+every new sentence (cosine 0.83–0.94 vs the anchor across novel lines).
+Inference is therefore persona-consistent per codename.
+
+## Data & license
+
+- **OpenSLR 83** — "Crowdsourced high-quality UK and Ireland English
+  Dialect speech data set" (Google, 2018–19), **CC BY-SA 4.0**.
+  Citation: Demirsahin et al., "Open-source Multi-speaker Corpora of
+  the English Accents in the British Isles", LREC 2020.
+- **CC BY-SA carries over to these voices**: derivatives (incl.
+  synthesized redistribution) inherit share-alike. This differs from
+  smoky (public-domain Hall corpus).
+- OpenSLR 83 offers 6 dialects × male/female; this release covers
+  Scottish (f+m), Irish (male), Welsh (f+m). The Irish female set is
+  not offered because OpenSLR 83 only ships `irish_english_male.zip`.
+- Audio: 48 kHz mono studio recordings → pooled 24 kHz clean sets with
+  light spectral-gate denoise, energy-VAD trim, SNR ≥ 8 dB filter,
+  per-pool caps (6 speakers / ~60 min / 10 min per speaker).
+
+## Training
+
+- **Base:** `FunAudioLLM/CosyVoice2-0.5B` (llm + flow + hift).
+- **Data:** pooled chunk sets → kaldi-style dirs (10% cv) → campplus
+  embeddings + speech tokens → parquet →
+  `cosyvoice/bin/train.py` (`--model llm`, 1×GPU, bf16 AMP,
+  constant-lr 1e-5, 60 epochs). One speaker ID per pool.
+- **Guarding (8 GB GPU):** bitsandbytes AdamW8bit; non-LLM params
+  frozen; bf16; gradient checkpointing; `KEEP_CKPT=12` in-run pruning
+  of checkpoints (multi-speaker SFT writes ~1 GB/epoch → ~60 GB if
+  unpruned).
+- **Outputs:** `llm_avg.pt` per voice (**best-8 by val loss** via
+  `average_model.py --val_best`); final voice dirs assembled with base
+  flow/hift + baked `spk2info.pt` + anchor + samples.
+
+## Evaluation
+
+- WER: whisper `medium.en` on novel pool dialect lines (see table;
+  target <12%; Scots lines orthography-inflated).
+  Tools: `experts/isles/eval_wer.py`, `eval_texts.py`.
+- Anonymization: `check_anon.py` — pooled embedding max cosine to a
+  member, per voice (see table).
+- Persona consistency: anchor-mode synthesis lands at cosine 0.83–0.94
+  vs the anchor across novel lines (vs 0.58 drift pre-fix).
+
+## Report to User
+
+- [x] Whisper WER < 12% on held-out lines (per voice; see table)
+- [x] Anonymization check (max cos 0.78–0.91)
+- [x] Persona-consistent anchored synthesis (0.83–0.94 vs anchor)
+- [x] All five voices signed off by listening; training data pruned
+- [ ] Publish zips via `publish_cosyvoice.py --voice ...` (or all)

anchor.txt

@@ -0,0 +1 @@
+Ah sure, we'll take the hurl down to the pitch if the rain holds off at all.

anchor.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f01d0d3b4695b4faacf71a3cc8b4e2300075a28bbd2102f63196069647badc4
+size 172878

campplus.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6ac6a63997761ae2997373e2ee1c47040854b4b759ea41ec48e4e42df0f4d73
+size 28303423

config.json

@@ -0,0 +1 @@
+{}

configuration.json

@@ -0,0 +1 @@
+{"framework":"Pytorch","task":"text-to-speech"}

cosyvoice2.yaml

@@ -0,0 +1,233 @@
+# set random seed, so that you may reproduce your result.
+__set_seed1: !apply:random.seed [1986]
+__set_seed2: !apply:numpy.random.seed [1986]
+__set_seed3: !apply:torch.manual_seed [1986]
+__set_seed4: !apply:torch.cuda.manual_seed_all [1986]
+
+# fixed params
+sample_rate: 24000
+llm_input_size: 896
+llm_output_size: 896
+spk_embed_dim: 192
+qwen_pretrain_path: ''
+token_frame_rate: 25
+token_mel_ratio: 2
+
+# stream related params
+chunk_size: 25 # streaming inference chunk size, in token
+num_decoding_left_chunks: -1 # streaming inference flow decoder left chunk size, <0 means use all left chunks
+
+# model params
+# for all class/function included in this repo, we use !<name> or !<new> for intialization, so that user may find all corresponding class/function according to one single yaml.
+# for system/third_party class/function, we do not require this.
+llm: !new:cosyvoice.llm.llm.Qwen2LM
+    llm_input_size: !ref <llm_input_size>
+    llm_output_size: !ref <llm_output_size>
+    speech_token_size: 6561
+    length_normalized_loss: True
+    lsm_weight: 0
+    mix_ratio: [5, 15]
+    llm: !new:cosyvoice.llm.llm.Qwen2Encoder
+        pretrain_path: !ref <qwen_pretrain_path>
+    sampling: !name:cosyvoice.utils.common.ras_sampling
+        top_p: 0.8
+        top_k: 25
+        win_size: 10
+        tau_r: 0.1
+
+flow: !new:cosyvoice.flow.flow.CausalMaskedDiffWithXvec
+    input_size: 512
+    output_size: 80
+    spk_embed_dim: !ref <spk_embed_dim>
+    output_type: 'mel'
+    vocab_size: 6561
+    input_frame_rate: !ref <token_frame_rate>
+    only_mask_loss: True
+    token_mel_ratio: !ref <token_mel_ratio>
+    pre_lookahead_len: 3
+    encoder: !new:cosyvoice.transformer.upsample_encoder.UpsampleConformerEncoder
+        output_size: 512
+        attention_heads: 8
+        linear_units: 2048
+        num_blocks: 6
+        dropout_rate: 0.1
+        positional_dropout_rate: 0.1
+        attention_dropout_rate: 0.1
+        normalize_before: True
+        input_layer: 'linear'
+        pos_enc_layer_type: 'rel_pos_espnet'
+        selfattention_layer_type: 'rel_selfattn'
+        input_size: 512
+        use_cnn_module: False
+        macaron_style: False
+        static_chunk_size: !ref <chunk_size>
+    decoder: !new:cosyvoice.flow.flow_matching.CausalConditionalCFM
+        in_channels: 240
+        n_spks: 1
+        spk_emb_dim: 80
+        cfm_params: !new:omegaconf.DictConfig
+            content:
+                sigma_min: 1e-06
+                solver: 'euler'
+                t_scheduler: 'cosine'
+                training_cfg_rate: 0.2
+                inference_cfg_rate: 0.7
+                reg_loss_type: 'l1'
+        estimator: !new:cosyvoice.flow.decoder.CausalConditionalDecoder
+            in_channels: 320
+            out_channels: 80
+            channels: [256]
+            dropout: 0.0
+            attention_head_dim: 64
+            n_blocks: 4
+            num_mid_blocks: 12
+            num_heads: 8
+            act_fn: 'gelu'
+            static_chunk_size: !ref <chunk_size> * <token_mel_ratio>
+            num_decoding_left_chunks: !ref <num_decoding_left_chunks>
+
+hift: !new:cosyvoice.hifigan.generator.HiFTGenerator
+    in_channels: 80
+    base_channels: 512
+    nb_harmonics: 8
+    sampling_rate: !ref <sample_rate>
+    nsf_alpha: 0.1
+    nsf_sigma: 0.003
+    nsf_voiced_threshold: 10
+    upsample_rates: [8, 5, 3]
+    upsample_kernel_sizes: [16, 11, 7]
+    istft_params:
+        n_fft: 16
+        hop_len: 4
+    resblock_kernel_sizes: [3, 7, 11]
+    resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5], [1, 3, 5]]
+    source_resblock_kernel_sizes: [7, 7, 11]
+    source_resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5], [1, 3, 5]]
+    lrelu_slope: 0.1
+    audio_limit: 0.99
+    f0_predictor: !new:cosyvoice.hifigan.f0_predictor.ConvRNNF0Predictor
+        num_class: 1
+        in_channels: 80
+        cond_channels: 512
+
+# gan related module
+mel_spec_transform1: !name:matcha.utils.audio.mel_spectrogram
+    n_fft: 1920
+    num_mels: 80
+    sampling_rate: !ref <sample_rate>
+    hop_size: 480
+    win_size: 1920
+    fmin: 0
+    fmax: null
+    center: False
+hifigan: !new:cosyvoice.hifigan.hifigan.HiFiGan
+    generator: !ref <hift>
+    discriminator: !new:cosyvoice.hifigan.discriminator.MultipleDiscriminator
+        mpd: !new:matcha.hifigan.models.MultiPeriodDiscriminator
+        mrd: !new:cosyvoice.hifigan.discriminator.MultiResSpecDiscriminator
+    mel_spec_transform: [
+        !ref <mel_spec_transform1>
+    ]
+
+# processor functions
+parquet_opener: !name:cosyvoice.dataset.processor.parquet_opener
+get_tokenizer: !name:cosyvoice.tokenizer.tokenizer.get_qwen_tokenizer
+    token_path: !ref <qwen_pretrain_path>
+    skip_special_tokens: True
+allowed_special: 'all'
+tokenize: !name:cosyvoice.dataset.processor.tokenize
+    get_tokenizer: !ref <get_tokenizer>
+    allowed_special: !ref <allowed_special>
+filter: !name:cosyvoice.dataset.processor.filter
+    max_length: 40960
+    min_length: 100
+    token_max_length: 200
+    token_min_length: 1
+resample: !name:cosyvoice.dataset.processor.resample
+    resample_rate: !ref <sample_rate>
+truncate: !name:cosyvoice.dataset.processor.truncate
+    truncate_length: 24480 # must be a multiplier of hop_size
+feat_extractor: !name:matcha.utils.audio.mel_spectrogram
+    n_fft: 1920
+    num_mels: 80
+    sampling_rate: !ref <sample_rate>
+    hop_size: 480
+    win_size: 1920
+    fmin: 0
+    fmax: 8000
+    center: False
+compute_fbank: !name:cosyvoice.dataset.processor.compute_fbank
+    feat_extractor: !ref <feat_extractor>
+compute_f0: !name:cosyvoice.dataset.processor.compute_f0
+    sample_rate: !ref <sample_rate>
+    hop_size: 480
+parse_embedding: !name:cosyvoice.dataset.processor.parse_embedding
+    normalize: True
+shuffle: !name:cosyvoice.dataset.processor.shuffle
+    shuffle_size: 1000
+sort: !name:cosyvoice.dataset.processor.sort
+    sort_size: 500  # sort_size should be less than shuffle_size
+batch: !name:cosyvoice.dataset.processor.batch
+    batch_type: 'dynamic'
+    max_frames_in_batch: 2000
+padding: !name:cosyvoice.dataset.processor.padding
+    use_spk_embedding: False # change to True during sft
+
+
+# dataset processor pipeline
+data_pipeline: [
+    !ref <parquet_opener>,
+    !ref <tokenize>,
+    !ref <filter>,
+    !ref <resample>,
+    !ref <compute_fbank>,
+    !ref <parse_embedding>,
+    !ref <shuffle>,
+    !ref <sort>,
+    !ref <batch>,
+    !ref <padding>,
+]
+data_pipeline_gan: [
+    !ref <parquet_opener>,
+    !ref <tokenize>,
+    !ref <filter>,
+    !ref <resample>,
+    !ref <truncate>,
+    !ref <compute_fbank>,
+    !ref <compute_f0>,
+    !ref <parse_embedding>,
+    !ref <shuffle>,
+    !ref <sort>,
+    !ref <batch>,
+    !ref <padding>,
+]
+
+# llm flow train conf
+train_conf:
+    optim: adam
+    optim_conf:
+        lr: 1e-5 # change to 1e-5 during sft
+    scheduler: constantlr # change to constantlr during sft
+    scheduler_conf:
+        warmup_steps: 2500
+    max_epoch: 200
+    grad_clip: 5
+    accum_grad: 2
+    log_interval: 100
+    save_per_step: -1
+
+# gan train conf
+train_conf_gan:
+    optim: adam
+    optim_conf:
+        lr: 0.0002 # use small lr for gan training
+    scheduler: constantlr
+    optim_d: adam
+    optim_conf_d:
+        lr: 0.0002 # use small lr for gan training
+    scheduler_d: constantlr
+    max_epoch: 200
+    grad_clip: 5
+    accum_grad: 1 # in gan training, accum_grad must be 1
+    log_interval: 100
+    save_per_step: -1

flow.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff4c2f867674411e0a08cee702996df13fa67c1cd864c06108da88d16d088541
+size 450575567

hift.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3386cc880324d4e98e05987b99107f49e40ed925b8ecc87c1f4939432d429879
+size 83390254

llm.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77fff91f5f29102fafb835e872cbab28ec6a5fe6519dfaf33216a013b0a30445
+size 1307514801

sample/sample_0.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f01d0d3b4695b4faacf71a3cc8b4e2300075a28bbd2102f63196069647badc4
+size 172878

sample/sample_1.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c9ed284cf11d39f1187c35fef1ca809e8b3d45bec14996e19971db7fd486415
+size 188238

sample/sample_2.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfc6d674e4888b346cbbe244db9106730c21d7c4a7ecdb45f7eb101e040a53d6
+size 165198

sample/sanity.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f01d0d3b4695b4faacf71a3cc8b4e2300075a28bbd2102f63196069647badc4
+size 172878

speech_tokenizer_v2.batch.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b45a98572ed21e3a3ebf50201f3020567f7db40e9a57509b790b2982f5c07b7
+size 496095794

speech_tokenizer_v2.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d43342aa12163a80bf07bffb94c9de2e120a8df2f9917cd2f642e7f4219c6f71
+size 496082973

spk2info.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69f873a9028f0cf443592c9914021abc96ced8135282762ee736c378ca67e2b9
+size 2416