Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ 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
+qwen0.6bemo4-merge/tokenizer.json filter=lfs diff=lfs merge=lfs -text

.mv

@@ -0,0 +1 @@
+Revision:master,CreatedAt:1759148356

README.md

@@ -0,0 +1,10 @@
+---
+license: apache-2.0
+language:
+- en
+---
+
+## Introduction
+- Converted weight files for: [IndexTTS-2-vLLM](https://github.com/Ksuriuri/index-tts-vllm)
+- Original project: [IndexTTS](https://github.com/index-tts/index-tts)
+- Original model weights: [IndexTTS-2](https://modelscope.cn/models/IndexTeam/IndexTTS-2)

bigvgan/bigvgan_generator.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e95ba25972d3de0628d99cd156e9315a9c018899bf739988959ebe3544080ced
+size 449228171

bigvgan/config.json

@@ -0,0 +1,63 @@
+{
+    "resblock": "1",
+    "num_gpus": 0,
+    "batch_size": 32,
+    "learning_rate": 0.0001,
+    "adam_b1": 0.8,
+    "adam_b2": 0.99,
+    "lr_decay": 0.9999996,
+    "seed": 1234,
+
+    "upsample_rates": [4,4,2,2,2,2],
+    "upsample_kernel_sizes": [8,8,4,4,4,4],
+    "upsample_initial_channel": 1536,
+    "resblock_kernel_sizes": [3,7,11],
+    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
+
+    "use_tanh_at_final": false,
+    "use_bias_at_final": false,
+
+    "activation": "snakebeta",
+    "snake_logscale": true,
+
+    "use_cqtd_instead_of_mrd": true,
+    "cqtd_filters": 128,
+    "cqtd_max_filters": 1024,
+    "cqtd_filters_scale": 1,
+    "cqtd_dilations": [1, 2, 4],
+    "cqtd_hop_lengths": [512, 256, 256],
+    "cqtd_n_octaves": [9, 9, 9],
+    "cqtd_bins_per_octaves": [24, 36, 48],
+
+    "mpd_reshapes": [2, 3, 5, 7, 11],
+    "use_spectral_norm": false,
+    "discriminator_channel_mult": 1,
+    
+    "use_multiscale_melloss": true,
+    "lambda_melloss": 15,
+
+    "clip_grad_norm": 500,
+
+    "segment_size": 65536,
+    "num_mels": 80,
+    "num_freq": 1025,
+    "n_fft": 1024,
+    "hop_size": 256,
+    "win_size": 1024,
+
+    "sampling_rate": 22050,
+
+    "fmin": 0,
+    "fmax": null,
+    "fmax_for_loss": null,
+
+    "normalize_volume": true,
+
+    "num_workers": 4,
+
+    "dist_config": {
+        "dist_backend": "nccl",
+        "dist_url": "tcp://localhost:54321",
+        "world_size": 1
+    }
+}

bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2a5ce8090d32da3642cc4f81fdc996376bc6dd3f4cd5e3d165f71120d9f2bc8
+size 475997

campplus/campplus_cn_common.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3388cf5fd3493c9ac9c69851d8e7a8badcfb4f3dc631020c4961371646d5ada8
+size 28036335

config.yaml

@@ -0,0 +1,120 @@
+dataset:
+    bpe_model: bpe.model
+    sample_rate: 24000
+    squeeze: false
+    mel:
+        sample_rate: 24000
+        n_fft: 1024
+        hop_length: 256
+        win_length: 1024
+        n_mels: 100
+        mel_fmin: 0
+        normalize: false
+
+gpt:
+    model_dim: 1280
+    max_mel_tokens: 1815
+    max_text_tokens: 600
+    heads: 20
+    use_mel_codes_as_input: true
+    mel_length_compression: 1024
+    layers: 24
+    number_text_tokens: 12000
+    number_mel_codes: 8194
+    start_mel_token: 8192
+    stop_mel_token: 8193
+    start_text_token: 0
+    stop_text_token: 1
+    train_solo_embeddings: false
+    condition_type: "conformer_perceiver"
+    condition_module:
+        output_size: 512
+        linear_units: 2048
+        attention_heads: 8
+        num_blocks: 6
+        input_layer: "conv2d2"
+        perceiver_mult: 2
+    emo_condition_module:
+        output_size: 512
+        linear_units: 1024
+        attention_heads: 4
+        num_blocks: 4
+        input_layer: "conv2d2"
+        perceiver_mult: 2
+
+semantic_codec:
+    codebook_size: 8192
+    hidden_size: 1024
+    codebook_dim: 8
+    vocos_dim: 384
+    vocos_intermediate_dim: 2048
+    vocos_num_layers: 12
+
+s2mel:
+    preprocess_params:
+        sr: 22050
+        spect_params:
+            n_fft: 1024
+            win_length: 1024
+            hop_length: 256
+            n_mels: 80
+            fmin: 0
+            fmax: "None"
+
+    dit_type: "DiT"
+    reg_loss_type: "l1"
+    style_encoder:
+        dim: 192
+    length_regulator:
+        channels: 512
+        is_discrete: false
+        in_channels: 1024
+        content_codebook_size: 2048
+        sampling_ratios: [1, 1, 1, 1]
+        vector_quantize: false
+        n_codebooks: 1
+        quantizer_dropout: 0.0
+        f0_condition: false
+        n_f0_bins: 512
+    DiT:
+        hidden_dim: 512
+        num_heads: 8
+        depth: 13
+        class_dropout_prob: 0.1
+        block_size: 8192
+        in_channels: 80
+        style_condition: true
+        final_layer_type: 'wavenet'
+        target: 'mel'
+        content_dim: 512
+        content_codebook_size: 1024
+        content_type: 'discrete'
+        f0_condition: false
+        n_f0_bins: 512
+        content_codebooks: 1
+        is_causal: false
+        long_skip_connection: true
+        zero_prompt_speech_token: false
+        time_as_token: false
+        style_as_token: false
+        uvit_skip_connection: true
+        add_resblock_in_transformer: false
+    wavenet:
+        hidden_dim: 512
+        num_layers: 8
+        kernel_size: 5
+        dilation_rate: 1
+        p_dropout: 0.2
+        style_condition: true
+
+gpt_checkpoint: gpt.pth
+w2v_stat: wav2vec2bert_stats.pt
+s2mel_checkpoint: s2mel.pth
+emo_matrix: feat2.pt 
+spk_matrix: feat1.pt
+emo_num: [3, 17, 2, 8, 4, 5, 10, 24]
+qwen_emo_path: qwen0.6bemo4-merge/ 
+vocoder:
+    type: "bigvgan"
+    name: "nvidia/bigvgan_v2_22khz_80band_256x"
+version: 2.0

configuration.json

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

feat1.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f219cb447d80216ba615666da2ff8d63ac544eee26657f3a7b278692bf7a67c4
+size 57170

feat2.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c4292e96dee535aea9a6206e9a0c856dd578dde9212acdb16dd3ada4d12bf80
+size 374866

gpt.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baaaeb8b56328da81731dc540a85a7dee32eca9da28f174b05757cb651c602a4
+size 3484663079

gpt/config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2InferenceModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 8192,
+  "dtype": "float16",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 8193,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 2417,
+  "n_embd": 1280,
+  "n_head": 20,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 1818,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 8194
+}

gpt/preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Qwen2AudioProcessor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

gpt/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaf87cd7c2d88cb5baef402c039f400501a83171cf651914fcc4cae6b1b8723d
+size 991248387

gpt/tokenizer_config.json

@@ -0,0 +1 @@
+{"model_max_length": 1024}

qwen0.6bemo4-merge/Modelfile

@@ -0,0 +1,11 @@
+# ollama modelfile auto-generated by llamafactory
+
+FROM .
+
+TEMPLATE """{{ if .System }}System: {{ .System }}<|endoftext|>
+{{ end }}{{ range .Messages }}{{ if eq .Role "user" }}Human: {{ .Content }}<|endoftext|>
+Assistant:{{ else if eq .Role "assistant" }}{{ .Content }}<|endoftext|>
+{{ end }}{{ end }}"""
+
+PARAMETER stop "<|endoftext|>"
+PARAMETER num_ctx 4096

qwen0.6bemo4-merge/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

qwen0.6bemo4-merge/chat_template.jinja

@@ -0,0 +1,4 @@
+{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ 'System: ' + system_message + '<|endoftext|>' + '
+' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '<|endoftext|>' + '
+Assistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '
+' }}{% endif %}{% endfor %}

qwen0.6bemo4-merge/config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

qwen0.6bemo4-merge/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.52.1"
+}

qwen0.6bemo4-merge/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11293257a8df593c154a8ecd5fc039f3076de35411e35f06d41b471e136f6641
+size 1192135096

qwen0.6bemo4-merge/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

qwen0.6bemo4-merge/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

qwen0.6bemo4-merge/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "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
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

s2mel.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aae1bb12017cbb47e7a5ce537fc82f40b6b1deb71acdb9b8f25686f32714b636
+size 1202198223

semantic_codec/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec947271175d8cad75ec37e83aa487e27c97a0f72a303393772da5ffa84bddf2
+size 177183712

w2v-bert-2.0/README.md

@@ -0,0 +1,184 @@
+---
+license: mit
+language:
+- af
+- am
+- ar
+- as
+- az
+- be
+- bn
+- bs
+- bg
+- ca
+- cs
+- zh
+- cy
+- da
+- de
+- el
+- en
+- et
+- fi
+- fr
+- or
+- om
+- ga
+- gl
+- gu
+- ha
+- he
+- hi
+- hr
+- hu
+- hy
+- ig
+- id
+- is
+- it
+- jv
+- ja
+- kn
+- ka
+- kk
+- mn
+- km
+- ky
+- ko
+- lo
+- ln
+- lt
+- lb
+- lg
+- lv
+- ml
+- mr
+- mk
+- mt
+- mi
+- my
+- nl
+- nb
+- ne
+- ny
+- oc
+- pa
+- ps
+- fa
+- pl
+- pt
+- ro
+- ru
+- sk
+- sl
+- sn
+- sd
+- so
+- es
+- sr
+- sv
+- sw
+- ta
+- te
+- tg
+- tl
+- th
+- tr
+- uk
+- ur
+- uz
+- vi
+- wo
+- xh
+- yo
+- ms
+- zu
+- ary
+- arz
+- yue
+- kea
+inference: false
+---
+# W2v-BERT 2.0 speech encoder
+
+We are open-sourcing our Conformer-based [W2v-BERT 2.0 speech encoder](#w2v-bert-20-speech-encoder) as described in Section 3.2.1 of the [paper](https://arxiv.org/pdf/2312.05187.pdf), which is at the core of our Seamless models.
+
+This model was pre-trained on 4.5M hours of unlabeled audio data covering more than 143 languages. It requires finetuning to be used for downstream tasks such as Automatic Speech Recognition (ASR), or Audio Classification.
+
+| Model Name        | #params | checkpoint                                                                                                                                                                                                                                                                                                                                                                 |
+| ----------------- | ------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| W2v-BERT 2.0 | 600M    | [checkpoint](https://huggingface.co/reach-vb/conformer-shaw/resolve/main/conformer_shaw.pt)
+
+**This model and its training are supported by 🤗 Transformers, more on it in the [docs](https://huggingface.co/docs/transformers/main/en/model_doc/wav2vec2-bert).**
+
+
+# 🤗 Transformers usage
+
+This is a bare checkpoint without any modeling head, and thus requires finetuning to be used for downstream tasks such as ASR. You can however use it to extract audio embeddings from the top layer with this code snippet:
+
+```python
+from transformers import AutoFeatureExtractor, Wav2Vec2BertModel
+import torch
+from datasets import load_dataset
+
+dataset = load_dataset("hf-internal-testing/librispeech_asr_demo", "clean", split="validation")
+dataset = dataset.sort("id")
+sampling_rate = dataset.features["audio"].sampling_rate
+
+processor = AutoProcessor.from_pretrained("facebook/w2v-bert-2.0")
+model = Wav2Vec2BertModel.from_pretrained("facebook/w2v-bert-2.0")
+
+# audio file is decoded on the fly
+inputs = processor(dataset[0]["audio"]["array"], sampling_rate=sampling_rate, return_tensors="pt")
+with torch.no_grad():
+    outputs = model(**inputs)
+```
+
+To learn more about the model use, refer to the following resources:
+- [its docs](https://huggingface.co/docs/transformers/main/en/model_doc/wav2vec2-bert)
+- [a blog post showing how to fine-tune it on Mongolian ASR](https://huggingface.co/blog/fine-tune-w2v2-bert)
+- [a training script example](https://github.com/huggingface/transformers/blob/main/examples/pytorch/speech-recognition/run_speech_recognition_ctc.py)
+
+
+# Seamless Communication usage
+
+This model can be used in [Seamless Communication](https://github.com/facebookresearch/seamless_communication), where it was released.
+ 
+Here's how to make a forward pass through the voice encoder, after having completed the [installation steps](https://github.com/facebookresearch/seamless_communication?tab=readme-ov-file#installation):
+
+```python
+import torch
+
+from fairseq2.data.audio import AudioDecoder, WaveformToFbankConverter
+from fairseq2.memory import MemoryBlock
+from fairseq2.nn.padding import get_seqs_and_padding_mask
+from pathlib import Path
+from seamless_communication.models.conformer_shaw import load_conformer_shaw_model
+
+
+audio_wav_path, device, dtype = ...
+audio_decoder = AudioDecoder(dtype=torch.float32, device=device)
+fbank_converter = WaveformToFbankConverter(
+    num_mel_bins=80,
+    waveform_scale=2**15,
+    channel_last=True,
+    standardize=True,
+    device=device,
+    dtype=dtype,
+)
+collater = Collater(pad_value=1)
+
+model = load_conformer_shaw_model("conformer_shaw", device=device, dtype=dtype)
+model.eval()
+
+with Path(audio_wav_path).open("rb") as fb:
+    block = MemoryBlock(fb.read())
+
+decoded_audio = audio_decoder(block)
+src = collater(fbank_converter(decoded_audio))["fbank"]
+seqs, padding_mask = get_seqs_and_padding_mask(src)
+
+with torch.inference_mode():
+  seqs, padding_mask = model.encoder_frontend(seqs, padding_mask)
+  seqs, padding_mask = model.encoder(seqs, padding_mask)
+```

w2v-bert-2.0/config.json

@@ -0,0 +1,81 @@
+{
+  "activation_dropout": 0.0,
+  "adapter_act": "relu",
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": false,
+  "architectures": [
+    "Wav2Vec2BertModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 768,
+  "codevector_dim": 768,
+  "conformer_conv_dropout": 0.1,
+  "contrastive_logits_temperature": 0.1,
+  "conv_depthwise_kernel_size": 31,
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "eos_token_id": 2,
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "feature_projection_input_dim": 160,
+  "final_dropout": 0.1,
+  "hidden_act": "swish",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "left_max_position_embeddings": 64,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_source_positions": 5000,
+  "model_type": "wav2vec2-bert",
+  "num_adapter_layers": 1,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 0,
+  "position_embeddings_type": "relative_key",
+  "proj_codevector_dim": 768,
+  "right_max_position_embeddings": 8,
+  "rotary_embedding_base": 10000,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0.dev0",
+  "use_intermediate_ffn_before_adapter": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": null,
+  "xvector_output_dim": 512
+}

w2v-bert-2.0/conformer_shaw.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8310b4270a5b499e92e20c859892dbf7429619347debb5f8feba79eb88f99b4f
+size 2329131983

w2v-bert-2.0/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb890c9660ed6e3414b6812e27257b8ce5454365d5490d3ad581ea60b93be043
+size 2322063736

w2v-bert-2.0/preprocessor_config.json

@@ -0,0 +1,11 @@
+{
+  "feature_extractor_type": "SeamlessM4TFeatureExtractor",
+  "feature_size": 80,
+  "num_mel_bins": 80,
+  "padding_side": "right",
+  "padding_value": 1,
+  "processor_class": "Wav2Vec2BertProcessor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "stride": 2
+}

wav2vec2bert_stats.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9c176c2b8850ab2e3ba828bbfa969deaf4566ce55db5f2687b8430b87526ad2
+size 9343